2025-09-14 15:21:13,823 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1108 [DEBUG]: logdir: _logs/noise-eval-v2/halfcheetah/bpql-noise_0.050-delay_24
2025-09-14 15:21:13,824 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1109 [DEBUG]: trainer_prefix: noise-eval-v2/halfcheetah/bpql-noise_0.050-delay_24
2025-09-14 15:21:13,824 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1110 [DEBUG]: args.trainer_eval_latencies: {'24': <latency_env.delayed_mdp.ConstantDelay object at 0x7f5f32697e60>}
2025-09-14 15:21:13,824 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1111 [DEBUG]: using device: cpu
2025-09-14 15:21:13,828 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1133 [INFO]: Creating new trainer
2025-09-14 15:21:13,935 baseline-bpql-noisepromille50-halfcheetah:113 [DEBUG]: pi network:
NNGaussianPolicy(
  (common_head): Sequential(
    (0): Flatten(start_dim=1, end_dim=-1)
    (1): Linear(in_features=161, out_features=256, bias=True)
    (2): ReLU()
    (3): Linear(in_features=256, out_features=256, bias=True)
    (4): ReLU()
  )
  (mu_head): Sequential(
    (0): Linear(in_features=256, out_features=6, bias=True)
    (1): Unflatten(dim=1, unflattened_size=(6,))
  )
  (log_std_head): Sequential(
    (0): Linear(in_features=256, out_features=6, bias=True)
    (1): Unflatten(dim=1, unflattened_size=(6,))
  )
  (tanh_refit): NNTanhRefit(scale: tensor([[2., 2., 2., 2., 2., 2.]]), shift: tensor([[-1., -1., -1., -1., -1., -1.]]))
)
2025-09-14 15:21:13,936 baseline-bpql-noisepromille50-halfcheetah:114 [DEBUG]: q network:
NNLayerConcat2(
  dim: -1
  (next): Sequential(
    (0): Linear(in_features=23, out_features=256, bias=True)
    (1): ReLU()
    (2): Linear(in_features=256, out_features=256, bias=True)
    (3): ReLU()
    (4): Linear(in_features=256, out_features=1, bias=True)
    (5): NNLayerSqueeze(dim: -1)
  )
  (init_left): Flatten(start_dim=1, end_dim=-1)
  (init_right): Flatten(start_dim=1, end_dim=-1)
)
2025-09-14 15:21:15,049 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1194 [DEBUG]: Starting training session...
2025-09-14 15:21:15,049 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 1/100
2025-09-14 15:23:38,983 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 15:23:49,237 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: -670.63538 ± 53.717
2025-09-14 15:23:49,238 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(-692.36896), np.float32(-703.7232), np.float32(-663.3258), np.float32(-705.7446), np.float32(-645.74133), np.float32(-668.0109), np.float32(-631.17377), np.float32(-766.9269), np.float32(-679.01855), np.float32(-550.32)]
2025-09-14 15:23:49,238 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 15:23:49,238 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (-670.64) for latency 24
2025-09-14 15:23:49,240 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 2/100 (estimated time remaining: 4 hours, 14 minutes, 24 seconds)
2025-09-14 15:26:21,116 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 15:26:30,163 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: -255.14619 ± 43.106
2025-09-14 15:26:30,163 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(-345.87125), np.float32(-287.3168), np.float32(-225.45068), np.float32(-199.10378), np.float32(-228.19926), np.float32(-302.5015), np.float32(-216.53853), np.float32(-244.18716), np.float32(-269.6081), np.float32(-232.68486)]
2025-09-14 15:26:30,163 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 15:26:30,163 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (-255.15) for latency 24
2025-09-14 15:26:30,166 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 3/100 (estimated time remaining: 4 hours, 17 minutes, 20 seconds)
2025-09-14 15:28:49,478 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 15:28:58,509 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: -131.83652 ± 54.339
2025-09-14 15:28:58,509 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(-189.76308), np.float32(-144.0641), np.float32(-218.3362), np.float32(-66.301575), np.float32(-52.81776), np.float32(-176.57777), np.float32(-71.447914), np.float32(-114.81294), np.float32(-111.69938), np.float32(-172.5446)]
2025-09-14 15:28:58,509 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 15:28:58,509 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (-131.84) for latency 24
2025-09-14 15:28:58,512 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 4/100 (estimated time remaining: 4 hours, 9 minutes, 45 seconds)
2025-09-14 15:31:18,014 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 15:31:27,070 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: -36.23307 ± 68.919
2025-09-14 15:31:27,070 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(-12.469906), np.float32(-53.716515), np.float32(-126.27033), np.float32(-19.092339), np.float32(-121.7846), np.float32(-103.00976), np.float32(69.69369), np.float32(82.881355), np.float32(-61.87858), np.float32(-16.683758)]
2025-09-14 15:31:27,070 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 15:31:27,071 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (-36.23) for latency 24
2025-09-14 15:31:27,073 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 5/100 (estimated time remaining: 4 hours, 4 minutes, 48 seconds)
2025-09-14 15:33:46,662 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 15:33:55,705 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 41.63935 ± 81.310
2025-09-14 15:33:55,706 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(79.89441), np.float32(-6.8448734), np.float32(54.069637), np.float32(-22.981153), np.float32(19.097376), np.float32(-67.925064), np.float32(-49.938206), np.float32(68.2967), np.float32(134.5948), np.float32(208.12985)]
2025-09-14 15:33:55,706 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 15:33:55,706 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (41.64) for latency 24
2025-09-14 15:33:55,708 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 6/100 (estimated time remaining: 4 hours, 52 seconds)
2025-09-14 15:36:16,774 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 15:36:25,798 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 234.49820 ± 103.412
2025-09-14 15:36:25,798 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(288.87064), np.float32(189.48534), np.float32(457.7318), np.float32(363.27072), np.float32(213.38428), np.float32(111.32364), np.float32(164.48874), np.float32(161.66525), np.float32(256.38596), np.float32(138.37549)]
2025-09-14 15:36:25,798 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 15:36:25,798 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (234.50) for latency 24
2025-09-14 15:36:25,800 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 7/100 (estimated time remaining: 3 hours, 57 minutes, 3 seconds)
2025-09-14 15:38:45,040 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 15:38:54,079 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 529.96881 ± 334.154
2025-09-14 15:38:54,079 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(417.33087), np.float32(793.3234), np.float32(788.6702), np.float32(698.40875), np.float32(356.2446), np.float32(-370.2386), np.float32(770.26807), np.float32(503.17517), np.float32(683.663), np.float32(658.8424)]
2025-09-14 15:38:54,079 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 15:38:54,079 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (529.97) for latency 24
2025-09-14 15:38:54,081 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 8/100 (estimated time remaining: 3 hours, 50 minutes, 36 seconds)
2025-09-14 15:41:13,291 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 15:41:22,350 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 775.40918 ± 152.566
2025-09-14 15:41:22,350 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(872.1198), np.float32(860.23267), np.float32(665.1289), np.float32(412.05603), np.float32(717.05634), np.float32(763.31305), np.float32(748.69653), np.float32(997.81744), np.float32(905.62396), np.float32(812.04675)]
2025-09-14 15:41:22,350 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 15:41:22,350 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (775.41) for latency 24
2025-09-14 15:41:22,353 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 9/100 (estimated time remaining: 3 hours, 48 minutes, 6 seconds)
2025-09-14 15:43:41,859 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 15:43:50,862 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 825.77673 ± 209.323
2025-09-14 15:43:50,862 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(816.61176), np.float32(1050.3014), np.float32(1036.1117), np.float32(466.03293), np.float32(435.1308), np.float32(788.8757), np.float32(803.81854), np.float32(1014.2073), np.float32(973.42505), np.float32(873.25275)]
2025-09-14 15:43:50,863 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 15:43:50,863 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (825.78) for latency 24
2025-09-14 15:43:50,865 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 10/100 (estimated time remaining: 3 hours, 45 minutes, 37 seconds)
2025-09-14 15:46:10,718 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 15:46:19,707 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1007.16522 ± 108.880
2025-09-14 15:46:19,707 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(958.1675), np.float32(970.50085), np.float32(1022.90393), np.float32(1138.2302), np.float32(727.73645), np.float32(1094.4141), np.float32(1077.132), np.float32(1050.8093), np.float32(1064.5248), np.float32(967.2332)]
2025-09-14 15:46:19,707 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 15:46:19,707 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (1007.17) for latency 24
2025-09-14 15:46:19,709 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 11/100 (estimated time remaining: 3 hours, 43 minutes, 12 seconds)
2025-09-14 15:48:39,692 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 15:48:48,737 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1011.72607 ± 159.188
2025-09-14 15:48:48,737 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1062.1758), np.float32(1113.924), np.float32(958.053), np.float32(973.5407), np.float32(1085.3658), np.float32(561.8738), np.float32(1053.7826), np.float32(1109.4384), np.float32(1071.7443), np.float32(1127.3622)]
2025-09-14 15:48:48,737 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 15:48:48,738 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (1011.73) for latency 24
2025-09-14 15:48:48,740 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 12/100 (estimated time remaining: 3 hours, 40 minutes, 24 seconds)
2025-09-14 15:51:08,668 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 15:51:17,705 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 962.87646 ± 174.750
2025-09-14 15:51:17,706 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1098.278), np.float32(977.4576), np.float32(1120.7137), np.float32(1020.4164), np.float32(522.2148), np.float32(955.7569), np.float32(1016.9521), np.float32(955.6712), np.float32(1154.9572), np.float32(806.3465)]
2025-09-14 15:51:17,706 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 15:51:17,708 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 13/100 (estimated time remaining: 3 hours, 38 minutes, 7 seconds)
2025-09-14 15:53:38,336 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 15:53:47,357 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 998.11267 ± 87.882
2025-09-14 15:53:47,357 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1021.4788), np.float32(1018.12054), np.float32(923.6981), np.float32(833.35376), np.float32(1066.567), np.float32(995.7402), np.float32(1051.1877), np.float32(872.9271), np.float32(1093.7594), np.float32(1104.294)]
2025-09-14 15:53:47,357 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 15:53:47,360 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 14/100 (estimated time remaining: 3 hours, 36 minutes, 3 seconds)
2025-09-14 15:56:07,244 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 15:56:16,300 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1080.98315 ± 62.817
2025-09-14 15:56:16,301 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1114.3278), np.float32(1106.705), np.float32(1025.7384), np.float32(1183.3463), np.float32(1098.5841), np.float32(1158.4929), np.float32(1020.1408), np.float32(971.3721), np.float32(1094.2595), np.float32(1036.8643)]
2025-09-14 15:56:16,301 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 15:56:16,301 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (1080.98) for latency 24
2025-09-14 15:56:16,304 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 15/100 (estimated time remaining: 3 hours, 33 minutes, 41 seconds)
2025-09-14 15:58:35,692 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 15:58:44,730 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 933.81134 ± 429.469
2025-09-14 15:58:44,730 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1022.886), np.float32(1027.0002), np.float32(938.70874), np.float32(1003.3182), np.float32(-296.04688), np.float32(1190.3114), np.float32(963.5078), np.float32(980.96295), np.float32(1118.0665), np.float32(1389.3987)]
2025-09-14 15:58:44,730 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 15:58:44,733 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 16/100 (estimated time remaining: 3 hours, 31 minutes, 5 seconds)
2025-09-14 16:01:04,863 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:01:13,895 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1121.67407 ± 127.229
2025-09-14 16:01:13,895 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1078.3232), np.float32(1124.4562), np.float32(1067.663), np.float32(1315.2311), np.float32(1162.2465), np.float32(1181.9614), np.float32(1084.4528), np.float32(1029.35), np.float32(860.75995), np.float32(1312.2981)]
2025-09-14 16:01:13,895 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:01:13,895 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (1121.67) for latency 24
2025-09-14 16:01:13,898 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 17/100 (estimated time remaining: 3 hours, 28 minutes, 38 seconds)
2025-09-14 16:03:33,660 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:03:42,659 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 801.92590 ± 697.448
2025-09-14 16:03:42,659 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1010.2095), np.float32(1210.571), np.float32(1025.0271), np.float32(1069.3367), np.float32(-540.2258), np.float32(1316.0768), np.float32(1176.369), np.float32(-622.7404), np.float32(1191.1241), np.float32(1183.5105)]
2025-09-14 16:03:42,659 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:03:42,662 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 18/100 (estimated time remaining: 3 hours, 26 minutes, 6 seconds)
2025-09-14 16:06:02,182 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:06:11,218 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1145.42432 ± 61.860
2025-09-14 16:06:11,218 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1161.7704), np.float32(1127.0411), np.float32(1118.556), np.float32(1120.7471), np.float32(1135.7068), np.float32(1179.0836), np.float32(1002.8377), np.float32(1216.5127), np.float32(1148.017), np.float32(1243.971)]
2025-09-14 16:06:11,218 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:06:11,218 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (1145.42) for latency 24
2025-09-14 16:06:11,221 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 19/100 (estimated time remaining: 3 hours, 23 minutes, 19 seconds)
2025-09-14 16:08:30,526 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:08:39,537 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1140.04858 ± 79.260
2025-09-14 16:08:39,537 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1152.7354), np.float32(1103.7417), np.float32(1149.987), np.float32(1225.2255), np.float32(1062.1454), np.float32(1098.1104), np.float32(1301.0697), np.float32(1135.868), np.float32(1001.15326), np.float32(1170.4504)]
2025-09-14 16:08:39,537 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:08:39,540 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 20/100 (estimated time remaining: 3 hours, 20 minutes, 40 seconds)
2025-09-14 16:10:59,366 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:11:08,381 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1206.24329 ± 102.068
2025-09-14 16:11:08,381 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1042.4414), np.float32(1171.0381), np.float32(1373.3279), np.float32(1261.3433), np.float32(1207.93), np.float32(1216.8617), np.float32(1359.4906), np.float32(1077.8369), np.float32(1216.3682), np.float32(1135.7949)]
2025-09-14 16:11:08,381 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:11:08,381 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (1206.24) for latency 24
2025-09-14 16:11:08,384 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 21/100 (estimated time remaining: 3 hours, 18 minutes, 18 seconds)
2025-09-14 16:13:28,004 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:13:37,010 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1259.34985 ± 174.670
2025-09-14 16:13:37,010 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1676.1787), np.float32(1022.0021), np.float32(1304.6779), np.float32(1166.8079), np.float32(1173.3582), np.float32(1119.4745), np.float32(1441.0918), np.float32(1226.1577), np.float32(1201.9124), np.float32(1261.8391)]
2025-09-14 16:13:37,010 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:13:37,010 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (1259.35) for latency 24
2025-09-14 16:13:37,013 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 22/100 (estimated time remaining: 3 hours, 15 minutes, 41 seconds)
2025-09-14 16:15:56,599 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:16:05,620 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1137.93286 ± 309.522
2025-09-14 16:16:05,620 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1120.5494), np.float32(1203.6329), np.float32(1047.39), np.float32(1308.8413), np.float32(1273.764), np.float32(1203.1213), np.float32(1444.3954), np.float32(1354.9279), np.float32(1152.0143), np.float32(270.6901)]
2025-09-14 16:16:05,620 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:16:05,623 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 23/100 (estimated time remaining: 3 hours, 13 minutes, 10 seconds)
2025-09-14 16:18:25,703 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:18:34,702 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1128.77319 ± 262.050
2025-09-14 16:18:34,702 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1331.1566), np.float32(1041.9513), np.float32(1126.8271), np.float32(1306.8723), np.float32(1386.2921), np.float32(402.23938), np.float32(1169.0858), np.float32(1185.5254), np.float32(1122.801), np.float32(1214.9816)]
2025-09-14 16:18:34,702 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:18:34,705 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 24/100 (estimated time remaining: 3 hours, 10 minutes, 49 seconds)
2025-09-14 16:20:54,564 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:21:03,607 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1155.93591 ± 378.036
2025-09-14 16:21:03,607 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1341.8181), np.float32(1470.933), np.float32(136.95892), np.float32(1634.7692), np.float32(1091.3956), np.float32(1285.4159), np.float32(1148.4799), np.float32(1183.4423), np.float32(1083.2965), np.float32(1182.8494)]
2025-09-14 16:21:03,607 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:21:03,610 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 25/100 (estimated time remaining: 3 hours, 8 minutes, 29 seconds)
2025-09-14 16:23:23,561 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:23:32,559 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1166.99402 ± 179.808
2025-09-14 16:23:32,559 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1257.191), np.float32(1284.9513), np.float32(913.5455), np.float32(900.0222), np.float32(1488.4247), np.float32(1374.7782), np.float32(1144.328), np.float32(1093.6986), np.float32(1051.4799), np.float32(1161.5212)]
2025-09-14 16:23:32,559 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:23:32,562 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 26/100 (estimated time remaining: 3 hours, 6 minutes, 2 seconds)
2025-09-14 16:25:52,623 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:26:01,653 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 968.74823 ± 542.070
2025-09-14 16:26:01,654 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1070.6733), np.float32(1509.0952), np.float32(1267.9938), np.float32(1158.73), np.float32(-14.988066), np.float32(1142.8318), np.float32(1435.6414), np.float32(959.85254), np.float32(-124.81067), np.float32(1282.4631)]
2025-09-14 16:26:01,654 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:26:01,657 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 27/100 (estimated time remaining: 3 hours, 3 minutes, 40 seconds)
2025-09-14 16:28:21,720 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:28:30,749 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1152.93262 ± 503.561
2025-09-14 16:28:30,749 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1391.666), np.float32(1190.4386), np.float32(1204.4211), np.float32(1576.4443), np.float32(147.81972), np.float32(1425.5538), np.float32(1634.2644), np.float32(1421.2148), np.float32(1321.8811), np.float32(215.62267)]
2025-09-14 16:28:30,749 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:28:30,752 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 28/100 (estimated time remaining: 3 hours, 1 minute, 18 seconds)
2025-09-14 16:30:50,221 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:30:59,219 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1383.36646 ± 195.739
2025-09-14 16:30:59,219 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1288.233), np.float32(1294.4877), np.float32(1300.4406), np.float32(1417.4897), np.float32(1894.0356), np.float32(1559.0591), np.float32(1335.9978), np.float32(1194.561), np.float32(1324.5721), np.float32(1224.7883)]
2025-09-14 16:30:59,219 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:30:59,219 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (1383.37) for latency 24
2025-09-14 16:30:59,222 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 29/100 (estimated time remaining: 2 hours, 58 minutes, 41 seconds)
2025-09-14 16:33:18,668 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:33:27,662 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1395.71191 ± 285.566
2025-09-14 16:33:27,662 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1473.57), np.float32(1125.77), np.float32(1153.065), np.float32(1581.2394), np.float32(1657.1708), np.float32(1146.4818), np.float32(1432.7689), np.float32(2036.4493), np.float32(1132.3065), np.float32(1218.2966)]
2025-09-14 16:33:27,662 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:33:27,662 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (1395.71) for latency 24
2025-09-14 16:33:27,666 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 30/100 (estimated time remaining: 2 hours, 56 minutes, 5 seconds)
2025-09-14 16:35:47,226 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:35:56,217 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1403.89087 ± 200.954
2025-09-14 16:35:56,217 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1361.9287), np.float32(1495.8606), np.float32(1612.7762), np.float32(1383.4543), np.float32(1382.6993), np.float32(1212.6564), np.float32(1823.0507), np.float32(1173.8899), np.float32(1470.6323), np.float32(1121.9609)]
2025-09-14 16:35:56,217 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:35:56,218 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (1403.89) for latency 24
2025-09-14 16:35:56,221 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 31/100 (estimated time remaining: 2 hours, 53 minutes, 31 seconds)
2025-09-14 16:38:15,879 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:38:24,853 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1114.89868 ± 341.797
2025-09-14 16:38:24,853 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1396.7328), np.float32(1166.5925), np.float32(1156.5696), np.float32(1675.7589), np.float32(1175.7147), np.float32(1235.8492), np.float32(1090.1676), np.float32(733.33624), np.float32(1178.7621), np.float32(339.50247)]
2025-09-14 16:38:24,853 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:38:24,857 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 32/100 (estimated time remaining: 2 hours, 50 minutes, 56 seconds)
2025-09-14 16:40:44,142 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:40:53,148 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1428.96558 ± 249.185
2025-09-14 16:40:53,149 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1914.2158), np.float32(1667.6698), np.float32(1294.5204), np.float32(1217.3658), np.float32(1037.9977), np.float32(1322.2734), np.float32(1483.9583), np.float32(1704.1752), np.float32(1339.2872), np.float32(1308.1929)]
2025-09-14 16:40:53,149 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:40:53,149 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (1428.97) for latency 24
2025-09-14 16:40:53,152 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 33/100 (estimated time remaining: 2 hours, 48 minutes, 16 seconds)
2025-09-14 16:43:13,052 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:43:22,020 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1434.59949 ± 506.480
2025-09-14 16:43:22,020 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1448.2072), np.float32(1302.596), np.float32(1743.9354), np.float32(313.8236), np.float32(1241.4802), np.float32(1699.4949), np.float32(1410.4028), np.float32(2464.3787), np.float32(1270.2698), np.float32(1451.4062)]
2025-09-14 16:43:22,020 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:43:22,020 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (1434.60) for latency 24
2025-09-14 16:43:22,024 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 34/100 (estimated time remaining: 2 hours, 45 minutes, 53 seconds)
2025-09-14 16:45:41,848 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:45:50,838 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1387.03040 ± 243.419
2025-09-14 16:45:50,838 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1664.3141), np.float32(1208.5769), np.float32(1157.0897), np.float32(1360.3895), np.float32(1110.8743), np.float32(1911.3397), np.float32(1169.6754), np.float32(1558.8186), np.float32(1390.0183), np.float32(1339.2069)]
2025-09-14 16:45:50,839 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:45:50,842 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 35/100 (estimated time remaining: 2 hours, 43 minutes, 29 seconds)
2025-09-14 16:48:10,510 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:48:19,521 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1131.57483 ± 555.678
2025-09-14 16:48:19,521 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(361.18124), np.float32(1459.858), np.float32(1724.709), np.float32(1241.0592), np.float32(1260.0847), np.float32(1220.0375), np.float32(1179.195), np.float32(1181.7197), np.float32(1800.0214), np.float32(-112.11719)]
2025-09-14 16:48:19,521 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:48:19,524 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 36/100 (estimated time remaining: 2 hours, 41 minutes, 2 seconds)
2025-09-14 16:50:39,651 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:50:48,657 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1334.11194 ± 397.654
2025-09-14 16:50:48,657 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1378.9305), np.float32(1302.2769), np.float32(1848.917), np.float32(1419.2452), np.float32(1660.3599), np.float32(1160.1764), np.float32(1277.3224), np.float32(295.74216), np.float32(1369.7761), np.float32(1628.3722)]
2025-09-14 16:50:48,657 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:50:48,660 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 37/100 (estimated time remaining: 2 hours, 38 minutes, 40 seconds)
2025-09-14 16:53:08,769 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:53:17,796 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1183.59900 ± 296.607
2025-09-14 16:53:17,796 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1566.8478), np.float32(1223.968), np.float32(1172.461), np.float32(1210.2128), np.float32(359.0581), np.float32(1325.8778), np.float32(1150.2347), np.float32(1322.5963), np.float32(1266.7411), np.float32(1237.992)]
2025-09-14 16:53:17,797 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:53:17,800 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 38/100 (estimated time remaining: 2 hours, 36 minutes, 22 seconds)
2025-09-14 16:55:37,688 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:55:46,688 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1399.23035 ± 546.029
2025-09-14 16:55:46,688 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(259.06512), np.float32(1168.63), np.float32(1307.7742), np.float32(1342.5016), np.float32(2182.1353), np.float32(2295.859), np.float32(1245.4637), np.float32(1738.6257), np.float32(1249.5027), np.float32(1202.7463)]
2025-09-14 16:55:46,689 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:55:46,692 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 39/100 (estimated time remaining: 2 hours, 33 minutes, 53 seconds)
2025-09-14 16:58:06,198 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 16:58:15,198 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1581.50159 ± 538.950
2025-09-14 16:58:15,198 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1674.2263), np.float32(1095.959), np.float32(1787.877), np.float32(1840.4653), np.float32(2110.6904), np.float32(2343.3293), np.float32(1164.6583), np.float32(365.06146), np.float32(1730.2001), np.float32(1702.5492)]
2025-09-14 16:58:15,198 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 16:58:15,198 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (1581.50) for latency 24
2025-09-14 16:58:15,202 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 40/100 (estimated time remaining: 2 hours, 31 minutes, 21 seconds)
2025-09-14 17:00:34,203 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:00:43,205 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1377.00476 ± 248.832
2025-09-14 17:00:43,205 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1213.9772), np.float32(1388.1638), np.float32(1196.8365), np.float32(1541.6132), np.float32(1213.9958), np.float32(1139.7644), np.float32(1222.3563), np.float32(1404.1742), np.float32(1421.4445), np.float32(2027.7219)]
2025-09-14 17:00:43,205 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:00:43,209 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 41/100 (estimated time remaining: 2 hours, 28 minutes, 44 seconds)
2025-09-14 17:03:02,561 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:03:11,549 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1546.59216 ± 275.832
2025-09-14 17:03:11,549 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1359.0458), np.float32(1790.6232), np.float32(1589.3865), np.float32(1713.5742), np.float32(1123.7687), np.float32(1530.7659), np.float32(1438.3075), np.float32(1307.8098), np.float32(2162.482), np.float32(1450.1578)]
2025-09-14 17:03:11,549 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:03:11,553 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 42/100 (estimated time remaining: 2 hours, 26 minutes, 6 seconds)
2025-09-14 17:05:30,923 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:05:39,913 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1699.20544 ± 442.502
2025-09-14 17:05:39,913 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1474.8568), np.float32(1203.856), np.float32(2180.965), np.float32(1338.9344), np.float32(2354.5676), np.float32(1716.8884), np.float32(2240.328), np.float32(1694.7843), np.float32(951.3635), np.float32(1835.5116)]
2025-09-14 17:05:39,913 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:05:39,913 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (1699.21) for latency 24
2025-09-14 17:05:39,917 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 43/100 (estimated time remaining: 2 hours, 23 minutes, 28 seconds)
2025-09-14 17:07:59,316 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:08:08,318 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1803.16992 ± 368.077
2025-09-14 17:08:08,318 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1628.3612), np.float32(1442.0927), np.float32(1293.5007), np.float32(1848.8428), np.float32(1935.4054), np.float32(1452.1152), np.float32(1797.4259), np.float32(2633.6147), np.float32(1890.6082), np.float32(2109.732)]
2025-09-14 17:08:08,318 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:08:08,318 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (1803.17) for latency 24
2025-09-14 17:08:08,322 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 44/100 (estimated time remaining: 2 hours, 20 minutes, 54 seconds)
2025-09-14 17:10:27,829 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:10:36,858 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1336.18530 ± 354.149
2025-09-14 17:10:36,858 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1247.0555), np.float32(1437.1906), np.float32(1618.6002), np.float32(1298.1403), np.float32(1330.7572), np.float32(617.60913), np.float32(1219.0688), np.float32(1059.2009), np.float32(2064.308), np.float32(1469.9214)]
2025-09-14 17:10:36,858 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:10:36,862 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 45/100 (estimated time remaining: 2 hours, 18 minutes, 26 seconds)
2025-09-14 17:12:56,809 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:13:05,977 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1317.56580 ± 523.294
2025-09-14 17:13:05,977 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1338.2708), np.float32(1551.5223), np.float32(234.67717), np.float32(1557.5443), np.float32(619.94507), np.float32(2194.8098), np.float32(1248.9142), np.float32(1694.2633), np.float32(1517.9534), np.float32(1217.7577)]
2025-09-14 17:13:05,977 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:13:05,981 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 46/100 (estimated time remaining: 2 hours, 16 minutes, 10 seconds)
2025-09-14 17:15:25,349 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:15:34,354 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 2000.60583 ± 477.475
2025-09-14 17:15:34,354 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1379.534), np.float32(2167.6946), np.float32(2731.991), np.float32(2674.91), np.float32(1866.6609), np.float32(2555.8318), np.float32(1705.4556), np.float32(1853.7904), np.float32(1470.7411), np.float32(1599.4515)]
2025-09-14 17:15:34,354 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:15:34,355 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (2000.61) for latency 24
2025-09-14 17:15:34,359 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 47/100 (estimated time remaining: 2 hours, 13 minutes, 42 seconds)
2025-09-14 17:17:53,852 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:18:02,872 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1877.18359 ± 641.071
2025-09-14 17:18:02,873 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(816.0763), np.float32(1459.1956), np.float32(2734.7551), np.float32(2372.2312), np.float32(2520.7908), np.float32(1244.707), np.float32(2008.6224), np.float32(1776.1072), np.float32(2620.8154), np.float32(1218.5352)]
2025-09-14 17:18:02,873 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:18:02,877 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 48/100 (estimated time remaining: 2 hours, 11 minutes, 15 seconds)
2025-09-14 17:20:22,253 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:20:31,232 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1965.79138 ± 683.429
2025-09-14 17:20:31,233 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1834.0056), np.float32(1323.3579), np.float32(2941.778), np.float32(2952.3208), np.float32(1326.0192), np.float32(2027.3671), np.float32(2968.9539), np.float32(1547.1255), np.float32(1426.0312), np.float32(1310.9543)]
2025-09-14 17:20:31,233 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:20:31,237 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 49/100 (estimated time remaining: 2 hours, 8 minutes, 46 seconds)
2025-09-14 17:22:50,808 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:22:59,816 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1847.76404 ± 530.833
2025-09-14 17:22:59,816 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1325.2599), np.float32(1750.3992), np.float32(1538.7952), np.float32(2910.9907), np.float32(2059.0889), np.float32(1316.8835), np.float32(1621.1296), np.float32(2502.7573), np.float32(1239.8608), np.float32(2212.4739)]
2025-09-14 17:22:59,816 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:22:59,820 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 50/100 (estimated time remaining: 2 hours, 6 minutes, 18 seconds)
2025-09-14 17:25:19,781 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:25:29,003 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1711.39917 ± 487.042
2025-09-14 17:25:29,003 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1233.0508), np.float32(1705.7173), np.float32(1462.559), np.float32(1369.6517), np.float32(2054.6191), np.float32(1257.1445), np.float32(2909.0278), np.float32(1354.5017), np.float32(1785.8488), np.float32(1981.8711)]
2025-09-14 17:25:29,003 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:25:29,007 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 51/100 (estimated time remaining: 2 hours, 3 minutes, 50 seconds)
2025-09-14 17:27:53,564 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:28:02,769 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 2154.07861 ± 646.719
2025-09-14 17:28:02,770 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(2741.335), np.float32(2897.973), np.float32(3003.231), np.float32(1926.3066), np.float32(2943.2278), np.float32(1372.4285), np.float32(1371.4957), np.float32(1516.4335), np.float32(1646.6765), np.float32(2121.6794)]
2025-09-14 17:28:02,770 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:28:02,770 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (2154.08) for latency 24
2025-09-14 17:28:02,774 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 52/100 (estimated time remaining: 2 hours, 2 minutes, 14 seconds)
2025-09-14 17:30:27,567 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:30:36,640 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1567.99390 ± 642.381
2025-09-14 17:30:36,640 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(2493.165), np.float32(1286.8512), np.float32(2109.783), np.float32(1255.5665), np.float32(2200.3333), np.float32(1789.6973), np.float32(104.13347), np.float32(1284.9377), np.float32(1830.9172), np.float32(1324.5562)]
2025-09-14 17:30:36,640 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:30:36,644 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 53/100 (estimated time remaining: 2 hours, 36 seconds)
2025-09-14 17:32:59,172 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:33:08,134 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1689.23657 ± 648.258
2025-09-14 17:33:08,134 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1272.7179), np.float32(1453.0194), np.float32(2053.7058), np.float32(1128.2124), np.float32(1288.0952), np.float32(3279.202), np.float32(1150.4812), np.float32(1505.9613), np.float32(2349.3198), np.float32(1411.6505)]
2025-09-14 17:33:08,134 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:33:08,139 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 54/100 (estimated time remaining: 1 hour, 58 minutes, 34 seconds)
2025-09-14 17:35:24,314 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:35:33,262 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 2287.21558 ± 534.202
2025-09-14 17:35:33,262 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1351.9174), np.float32(2060.4602), np.float32(1786.0063), np.float32(2647.5396), np.float32(2443.6), np.float32(2933.6733), np.float32(2263.5452), np.float32(3037.0815), np.float32(1666.3805), np.float32(2681.951)]
2025-09-14 17:35:33,262 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:35:33,262 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (2287.22) for latency 24
2025-09-14 17:35:33,267 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 55/100 (estimated time remaining: 1 hour, 55 minutes, 31 seconds)
2025-09-14 17:38:08,086 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:38:17,278 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1724.22034 ± 290.598
2025-09-14 17:38:17,278 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1533.7064), np.float32(2074.4216), np.float32(2102.8904), np.float32(2133.9946), np.float32(1886.7443), np.float32(1435.0449), np.float32(1520.2354), np.float32(1770.656), np.float32(1395.8021), np.float32(1388.7075)]
2025-09-14 17:38:17,278 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:38:17,283 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 56/100 (estimated time remaining: 1 hour, 55 minutes, 14 seconds)
2025-09-14 17:41:08,552 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:41:19,165 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1854.89197 ± 880.281
2025-09-14 17:41:19,165 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(436.19376), np.float32(1722.91), np.float32(1401.6064), np.float32(2943.5562), np.float32(356.8969), np.float32(1630.905), np.float32(2842.075), np.float32(2160.487), np.float32(2703.5598), np.float32(2350.729)]
2025-09-14 17:41:19,165 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:41:19,172 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 57/100 (estimated time remaining: 1 hour, 56 minutes, 48 seconds)
2025-09-14 17:44:22,046 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:44:32,128 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1847.55725 ± 918.654
2025-09-14 17:44:32,128 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1490.418), np.float32(2258.2117), np.float32(1870.3625), np.float32(-56.255306), np.float32(2819.4644), np.float32(1535.0706), np.float32(2429.6133), np.float32(1167.1101), np.float32(3448.2678), np.float32(1513.3085)]
2025-09-14 17:44:32,128 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:44:32,134 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 58/100 (estimated time remaining: 1 hour, 59 minutes, 45 seconds)
2025-09-14 17:47:35,361 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:47:45,589 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 2026.44116 ± 591.661
2025-09-14 17:47:45,590 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1188.5126), np.float32(2764.242), np.float32(1292.4122), np.float32(2611.7751), np.float32(1796.0057), np.float32(2461.9553), np.float32(2905.3342), np.float32(1646.062), np.float32(1565.1555), np.float32(2032.9567)]
2025-09-14 17:47:45,590 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:47:45,596 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 59/100 (estimated time remaining: 2 hours, 2 minutes, 50 seconds)
2025-09-14 17:50:47,843 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:50:57,914 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 1776.12463 ± 605.421
2025-09-14 17:50:57,915 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(2003.6661), np.float32(1591.6735), np.float32(1407.935), np.float32(2277.7588), np.float32(1837.7), np.float32(411.46262), np.float32(2298.188), np.float32(2765.7864), np.float32(1590.4486), np.float32(1576.6278)]
2025-09-14 17:50:57,915 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:50:57,921 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 60/100 (estimated time remaining: 2 hours, 6 minutes, 22 seconds)
2025-09-14 17:54:00,483 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:54:10,584 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 2130.67676 ± 736.249
2025-09-14 17:54:10,584 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1281.4017), np.float32(3600.1777), np.float32(2326.6387), np.float32(2490.6006), np.float32(1785.8734), np.float32(2730.5798), np.float32(2779.8862), np.float32(1475.097), np.float32(1302.3605), np.float32(1534.1521)]
2025-09-14 17:54:10,584 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:54:10,590 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 61/100 (estimated time remaining: 2 hours, 7 minutes, 6 seconds)
2025-09-14 17:57:12,817 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 17:57:22,887 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 2841.42188 ± 927.973
2025-09-14 17:57:22,887 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(2766.529), np.float32(1661.9946), np.float32(3659.0374), np.float32(2985.2427), np.float32(3871.417), np.float32(3649.329), np.float32(1302.8615), np.float32(3893.306), np.float32(1688.4606), np.float32(2936.0386)]
2025-09-14 17:57:22,887 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 17:57:22,887 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (2841.42) for latency 24
2025-09-14 17:57:22,893 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 62/100 (estimated time remaining: 2 hours, 5 minutes, 17 seconds)
2025-09-14 18:00:25,398 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:00:35,471 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3307.11719 ± 980.605
2025-09-14 18:00:35,471 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1722.0107), np.float32(3842.243), np.float32(4025.5378), np.float32(4236.7246), np.float32(4075.2673), np.float32(3217.338), np.float32(2518.224), np.float32(3875.671), np.float32(1487.7084), np.float32(4070.4475)]
2025-09-14 18:00:35,471 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:00:35,471 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (3307.12) for latency 24
2025-09-14 18:00:35,477 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 63/100 (estimated time remaining: 2 hours, 2 minutes, 1 second)
2025-09-14 18:03:37,203 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:03:47,268 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 2451.92236 ± 1186.136
2025-09-14 18:03:47,268 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(3395.494), np.float32(1496.7163), np.float32(4011.4204), np.float32(1311.3918), np.float32(3663.0933), np.float32(1251.3076), np.float32(1146.7986), np.float32(1187.0217), np.float32(3473.0964), np.float32(3582.884)]
2025-09-14 18:03:47,269 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:03:47,275 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 64/100 (estimated time remaining: 1 hour, 58 minutes, 36 seconds)
2025-09-14 18:06:49,300 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:06:59,419 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 2209.66650 ± 901.618
2025-09-14 18:06:59,420 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(3723.3633), np.float32(2163.2993), np.float32(2249.0662), np.float32(2358.5972), np.float32(1251.1011), np.float32(3798.9583), np.float32(1518.1318), np.float32(1176.2534), np.float32(1352.9601), np.float32(2504.9307)]
2025-09-14 18:06:59,420 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:06:59,426 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 65/100 (estimated time remaining: 1 hour, 55 minutes, 22 seconds)
2025-09-14 18:10:01,327 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:10:11,486 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3075.53735 ± 1148.217
2025-09-14 18:10:11,486 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(3581.6096), np.float32(3979.4924), np.float32(4083.9512), np.float32(2022.5803), np.float32(1298.1196), np.float32(4699.6226), np.float32(4399.078), np.float32(2593.3804), np.float32(2267.357), np.float32(1830.1809)]
2025-09-14 18:10:11,486 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:10:11,493 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 66/100 (estimated time remaining: 1 hour, 52 minutes, 6 seconds)
2025-09-14 18:13:13,864 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:13:23,943 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 2661.69385 ± 909.594
2025-09-14 18:13:23,943 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(3992.973), np.float32(2906.077), np.float32(3296.4136), np.float32(3966.645), np.float32(2266.3032), np.float32(1445.7422), np.float32(1415.6531), np.float32(2504.5842), np.float32(1704.7935), np.float32(3117.755)]
2025-09-14 18:13:23,943 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:13:23,949 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 67/100 (estimated time remaining: 1 hour, 48 minutes, 55 seconds)
2025-09-14 18:16:26,178 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:16:36,226 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 2688.19653 ± 1101.185
2025-09-14 18:16:36,227 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1241.1394), np.float32(3378.7205), np.float32(3736.6677), np.float32(1729.9955), np.float32(3136.5293), np.float32(1030.177), np.float32(4356.67), np.float32(2156.1938), np.float32(2268.1392), np.float32(3847.7334)]
2025-09-14 18:16:36,227 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:16:36,233 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 68/100 (estimated time remaining: 1 hour, 45 minutes, 40 seconds)
2025-09-14 18:19:38,032 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:19:48,098 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 2763.51538 ± 1230.253
2025-09-14 18:19:48,098 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4204.851), np.float32(4070.715), np.float32(2586.8455), np.float32(1903.5388), np.float32(4278.822), np.float32(1197.6119), np.float32(1742.2562), np.float32(4261.7666), np.float32(2052.262), np.float32(1336.485)]
2025-09-14 18:19:48,098 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:19:48,104 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 69/100 (estimated time remaining: 1 hour, 42 minutes, 29 seconds)
2025-09-14 18:22:39,989 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:22:49,928 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3852.20630 ± 1018.735
2025-09-14 18:22:49,929 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4370.958), np.float32(4397.0825), np.float32(4711.304), np.float32(4562.453), np.float32(4399.228), np.float32(3953.1296), np.float32(4041.85), np.float32(2513.8154), np.float32(4228.3364), np.float32(1343.9065)]
2025-09-14 18:22:49,929 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:22:49,929 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (3852.21) for latency 24
2025-09-14 18:22:49,935 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 70/100 (estimated time remaining: 1 hour, 38 minutes, 13 seconds)
2025-09-14 18:25:40,832 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:25:50,817 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 2356.28662 ± 777.438
2025-09-14 18:25:50,818 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1362.6456), np.float32(2168.6057), np.float32(3030.3674), np.float32(1845.9313), np.float32(3413.9414), np.float32(1778.4348), np.float32(1947.207), np.float32(1609.6405), np.float32(2613.4226), np.float32(3792.6726)]
2025-09-14 18:25:50,818 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:25:50,824 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 71/100 (estimated time remaining: 1 hour, 33 minutes, 55 seconds)
2025-09-14 18:28:41,717 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:28:51,730 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3518.31592 ± 1202.289
2025-09-14 18:28:51,731 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1221.4017), np.float32(4361.4927), np.float32(4480.0527), np.float32(4155.23), np.float32(4299.5083), np.float32(3847.4092), np.float32(4290.978), np.float32(1212.9219), np.float32(4141.1855), np.float32(3172.9802)]
2025-09-14 18:28:51,731 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:28:51,736 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 72/100 (estimated time remaining: 1 hour, 29 minutes, 41 seconds)
2025-09-14 18:31:42,706 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:31:52,431 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3528.25146 ± 966.629
2025-09-14 18:31:52,431 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4341.2456), np.float32(4779.244), np.float32(2814.3655), np.float32(2813.494), np.float32(4204.639), np.float32(4209.2046), np.float32(3988.9028), np.float32(1959.9097), np.float32(2058.0), np.float32(4113.5107)]
2025-09-14 18:31:52,432 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:31:52,438 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 73/100 (estimated time remaining: 1 hour, 25 minutes, 30 seconds)
2025-09-14 18:34:35,133 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:34:44,352 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3697.38428 ± 951.077
2025-09-14 18:34:44,353 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4250.607), np.float32(4435.682), np.float32(1441.3055), np.float32(4156.554), np.float32(4272.2964), np.float32(4235.2603), np.float32(3088.1768), np.float32(3642.326), np.float32(2751.6514), np.float32(4699.9844)]
2025-09-14 18:34:44,353 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:34:44,359 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 74/100 (estimated time remaining: 1 hour, 20 minutes, 39 seconds)
2025-09-14 18:37:24,168 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:37:33,318 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 2850.69922 ± 1618.984
2025-09-14 18:37:33,318 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1612.4767), np.float32(3933.925), np.float32(3216.198), np.float32(-4.316172), np.float32(4223.5435), np.float32(3972.4744), np.float32(24.457817), np.float32(3091.3179), np.float32(4599.019), np.float32(3837.8962)]
2025-09-14 18:37:33,318 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:37:33,323 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 75/100 (estimated time remaining: 1 hour, 16 minutes, 33 seconds)
2025-09-14 18:40:03,850 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:40:12,788 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 4355.54590 ± 249.392
2025-09-14 18:40:12,788 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4091.5242), np.float32(4437.8477), np.float32(4380.2207), np.float32(4587.3984), np.float32(4376.585), np.float32(4438.66), np.float32(4532.823), np.float32(3715.1453), np.float32(4528.0864), np.float32(4467.165)]
2025-09-14 18:40:12,788 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:40:12,788 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (4355.55) for latency 24
2025-09-14 18:40:12,793 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 76/100 (estimated time remaining: 1 hour, 11 minutes, 49 seconds)
2025-09-14 18:42:29,521 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:42:38,479 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3564.72339 ± 1159.277
2025-09-14 18:42:38,480 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4614.33), np.float32(4302.877), np.float32(4722.362), np.float32(4436.828), np.float32(3716.5881), np.float32(1699.4814), np.float32(2794.65), np.float32(4281.137), np.float32(3760.42), np.float32(1318.5626)]
2025-09-14 18:42:38,480 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:42:38,485 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 77/100 (estimated time remaining: 1 hour, 6 minutes, 8 seconds)
2025-09-14 18:44:55,381 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:45:04,322 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3386.12036 ± 1125.029
2025-09-14 18:45:04,322 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4471.1465), np.float32(1237.4796), np.float32(3526.1877), np.float32(4429.7715), np.float32(2448.1086), np.float32(3463.1768), np.float32(3953.6072), np.float32(1704.8973), np.float32(4308.6265), np.float32(4318.2)]
2025-09-14 18:45:04,322 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:45:04,328 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 78/100 (estimated time remaining: 1 hour, 42 seconds)
2025-09-14 18:47:13,203 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:47:22,136 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 2206.28955 ± 1057.634
2025-09-14 18:47:22,136 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1473.0116), np.float32(1492.6304), np.float32(2137.782), np.float32(2226.0342), np.float32(4242.036), np.float32(1337.3414), np.float32(4229.817), np.float32(1771.3995), np.float32(1856.7867), np.float32(1296.0571)]
2025-09-14 18:47:22,136 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:47:22,142 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 79/100 (estimated time remaining: 55 minutes, 34 seconds)
2025-09-14 18:49:29,117 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:49:38,056 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3263.24756 ± 1031.157
2025-09-14 18:49:38,056 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4057.2322), np.float32(4532.13), np.float32(2698.0095), np.float32(3443.9465), np.float32(3947.3977), np.float32(2009.4298), np.float32(3495.4663), np.float32(1412.9734), np.float32(4611.7754), np.float32(2424.1135)]
2025-09-14 18:49:38,056 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:49:38,062 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 80/100 (estimated time remaining: 50 minutes, 43 seconds)
2025-09-14 18:51:46,398 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:51:55,339 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3562.73584 ± 1266.062
2025-09-14 18:51:55,339 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4300.102), np.float32(2965.6365), np.float32(2959.6992), np.float32(1318.3862), np.float32(4308.6357), np.float32(4609.3813), np.float32(1371.3517), np.float32(4632.3223), np.float32(4749.3174), np.float32(4412.5273)]
2025-09-14 18:51:55,339 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:51:55,345 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 81/100 (estimated time remaining: 46 minutes, 50 seconds)
2025-09-14 18:54:03,212 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:54:12,156 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3276.51514 ± 1217.423
2025-09-14 18:54:12,156 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4400.199), np.float32(1372.48), np.float32(2530.2437), np.float32(3404.1152), np.float32(4282.4346), np.float32(4290.787), np.float32(4341.96), np.float32(4478.2886), np.float32(2365.4812), np.float32(1299.1622)]
2025-09-14 18:54:12,156 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:54:12,161 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 82/100 (estimated time remaining: 43 minutes, 55 seconds)
2025-09-14 18:56:19,943 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:56:28,895 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 4372.13770 ± 111.133
2025-09-14 18:56:28,895 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4286.811), np.float32(4500.9224), np.float32(4513.7173), np.float32(4187.6396), np.float32(4376.836), np.float32(4366.405), np.float32(4297.2056), np.float32(4409.9507), np.float32(4253.5605), np.float32(4528.3267)]
2025-09-14 18:56:28,895 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:56:28,895 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (4372.14) for latency 24
2025-09-14 18:56:28,900 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 83/100 (estimated time remaining: 41 minutes, 4 seconds)
2025-09-14 18:58:36,762 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 18:58:45,695 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3751.14697 ± 1026.853
2025-09-14 18:58:45,695 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4133.913), np.float32(4138.296), np.float32(1471.751), np.float32(4296.283), np.float32(4175.5977), np.float32(4164.391), np.float32(4428.753), np.float32(4380.7373), np.float32(4354.9727), np.float32(1966.7737)]
2025-09-14 18:58:45,695 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 18:58:45,700 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 84/100 (estimated time remaining: 38 minutes, 44 seconds)
2025-09-14 19:00:53,787 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 19:01:02,719 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 4155.38916 ± 845.697
2025-09-14 19:01:02,719 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(3883.5215), np.float32(4323.364), np.float32(4402.3228), np.float32(4375.69), np.float32(4316.8706), np.float32(4702.1797), np.float32(4692.408), np.float32(1711.7322), np.float32(4631.492), np.float32(4514.31)]
2025-09-14 19:01:02,719 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 19:01:02,725 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 85/100 (estimated time remaining: 36 minutes, 30 seconds)
2025-09-14 19:03:10,960 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 19:03:19,891 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 4312.62988 ± 807.073
2025-09-14 19:03:19,891 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4497.928), np.float32(4397.1196), np.float32(4678.734), np.float32(4824.5864), np.float32(4705.0728), np.float32(4509.3013), np.float32(4458.54), np.float32(1919.7092), np.float32(4622.111), np.float32(4513.1953)]
2025-09-14 19:03:19,891 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 19:03:19,896 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 86/100 (estimated time remaining: 34 minutes, 13 seconds)
2025-09-14 19:05:27,776 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 19:05:36,739 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3726.17969 ± 1553.525
2025-09-14 19:05:36,739 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1343.4854), np.float32(4668.318), np.float32(4581.2705), np.float32(4713.758), np.float32(4365.452), np.float32(3482.8406), np.float32(4742.6787), np.float32(4692.308), np.float32(149.24498), np.float32(4522.4414)]
2025-09-14 19:05:36,739 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 19:05:36,745 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 87/100 (estimated time remaining: 31 minutes, 56 seconds)
2025-09-14 19:07:45,184 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 19:07:54,112 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3445.93896 ± 1260.157
2025-09-14 19:07:54,112 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4535.5645), np.float32(1996.8469), np.float32(4680.61), np.float32(4214.1953), np.float32(1510.2955), np.float32(4349.7085), np.float32(1857.1565), np.float32(4537.297), np.float32(4435.9663), np.float32(2341.7527)]
2025-09-14 19:07:54,112 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 19:07:54,118 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 88/100 (estimated time remaining: 29 minutes, 41 seconds)
2025-09-14 19:10:01,866 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 19:10:10,799 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 4516.66650 ± 222.236
2025-09-14 19:10:10,799 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4672.0493), np.float32(4699.3394), np.float32(4679.5386), np.float32(4669.3306), np.float32(4701.834), np.float32(4489.8145), np.float32(4396.0283), np.float32(4434.6816), np.float32(3943.0981), np.float32(4480.951)]
2025-09-14 19:10:10,799 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 19:10:10,799 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1226 [INFO]: New best (4516.67) for latency 24
2025-09-14 19:10:10,804 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 89/100 (estimated time remaining: 27 minutes, 24 seconds)
2025-09-14 19:12:18,836 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 19:12:27,802 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3186.60303 ± 1448.377
2025-09-14 19:12:27,802 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(1481.3208), np.float32(4464.866), np.float32(4358.7944), np.float32(2436.4446), np.float32(2216.9077), np.float32(2746.86), np.float32(436.9969), np.float32(4504.7017), np.float32(4704.912), np.float32(4514.2256)]
2025-09-14 19:12:27,802 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 19:12:27,808 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 90/100 (estimated time remaining: 25 minutes, 7 seconds)
2025-09-14 19:14:35,791 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 19:14:44,732 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3956.46948 ± 986.596
2025-09-14 19:14:44,732 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4675.78), np.float32(4494.8975), np.float32(4631.3765), np.float32(4457.8135), np.float32(4731.8623), np.float32(4729.7417), np.float32(2017.9264), np.float32(2757.915), np.float32(2676.8345), np.float32(4390.546)]
2025-09-14 19:14:44,732 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 19:14:44,738 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 91/100 (estimated time remaining: 22 minutes, 49 seconds)
2025-09-14 19:16:52,305 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 19:17:01,233 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 4420.92432 ± 301.243
2025-09-14 19:17:01,233 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4758.9287), np.float32(4413.584), np.float32(3765.0212), np.float32(4433.364), np.float32(4607.796), np.float32(3968.4836), np.float32(4729.311), np.float32(4461.2354), np.float32(4542.198), np.float32(4529.315)]
2025-09-14 19:17:01,233 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 19:17:01,242 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 92/100 (estimated time remaining: 20 minutes, 32 seconds)
2025-09-14 19:19:09,186 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 19:19:18,123 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3865.25073 ± 1071.682
2025-09-14 19:19:18,123 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4589.4146), np.float32(1915.0852), np.float32(3839.4417), np.float32(4824.1816), np.float32(4328.5327), np.float32(4659.027), np.float32(1711.3341), np.float32(3883.0317), np.float32(4269.4175), np.float32(4633.045)]
2025-09-14 19:19:18,123 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 19:19:18,130 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 93/100 (estimated time remaining: 18 minutes, 14 seconds)
2025-09-14 19:21:25,840 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 19:21:34,796 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3874.49561 ± 1224.969
2025-09-14 19:21:34,796 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4696.583), np.float32(4345.6514), np.float32(4509.4756), np.float32(3932.0076), np.float32(1294.243), np.float32(1656.31), np.float32(4723.214), np.float32(4268.456), np.float32(4572.577), np.float32(4746.438)]
2025-09-14 19:21:34,796 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 19:21:34,802 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 94/100 (estimated time remaining: 15 minutes, 57 seconds)
2025-09-14 19:23:42,559 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 19:23:51,512 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 4024.31177 ± 959.442
2025-09-14 19:23:51,512 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4146.363), np.float32(4606.4834), np.float32(4885.006), np.float32(4728.604), np.float32(3378.6711), np.float32(4504.5146), np.float32(4599.495), np.float32(2042.7516), np.float32(2565.0732), np.float32(4786.1562)]
2025-09-14 19:23:51,512 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 19:23:51,518 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 95/100 (estimated time remaining: 13 minutes, 40 seconds)
2025-09-14 19:25:59,356 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 19:26:08,308 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3939.22412 ± 1315.849
2025-09-14 19:26:08,308 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4546.722), np.float32(4676.691), np.float32(4767.8315), np.float32(4379.613), np.float32(4588.7646), np.float32(2051.8208), np.float32(4520.607), np.float32(4356.6675), np.float32(4777.171), np.float32(726.35333)]
2025-09-14 19:26:08,308 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 19:26:08,314 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 96/100 (estimated time remaining: 11 minutes, 23 seconds)
2025-09-14 19:28:13,034 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 19:28:21,976 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 4284.04932 ± 882.049
2025-09-14 19:28:21,976 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4748.167), np.float32(4527.2603), np.float32(1818.3717), np.float32(3701.9294), np.float32(4655.199), np.float32(4806.384), np.float32(4377.27), np.float32(4869.4), np.float32(4545.829), np.float32(4790.681)]
2025-09-14 19:28:21,976 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 19:28:21,982 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 97/100 (estimated time remaining: 9 minutes, 4 seconds)
2025-09-14 19:30:26,563 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 19:30:35,508 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 4085.22803 ± 1039.847
2025-09-14 19:30:35,509 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4740.452), np.float32(1273.4481), np.float32(4721.312), np.float32(3163.122), np.float32(4234.412), np.float32(4666.7036), np.float32(4594.073), np.float32(4668.672), np.float32(4583.232), np.float32(4206.855)]
2025-09-14 19:30:35,509 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 19:30:35,515 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 98/100 (estimated time remaining: 6 minutes, 46 seconds)
2025-09-14 19:32:40,500 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 19:32:49,424 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3161.46631 ± 1400.205
2025-09-14 19:32:49,424 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(2076.1907), np.float32(2551.9414), np.float32(1292.2223), np.float32(4680.7617), np.float32(1672.9613), np.float32(4502.6924), np.float32(4777.8306), np.float32(3893.3872), np.float32(1489.7621), np.float32(4676.9165)]
2025-09-14 19:32:49,424 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 19:32:49,430 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 99/100 (estimated time remaining: 4 minutes, 29 seconds)
2025-09-14 19:34:54,166 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 19:35:03,105 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 4283.70850 ± 1002.954
2025-09-14 19:35:03,105 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(4801.9917), np.float32(1317.2354), np.float32(4519.8623), np.float32(4639.3394), np.float32(4740.4043), np.float32(4673.437), np.float32(4672.0933), np.float32(4322.5366), np.float32(4324.3726), np.float32(4825.817)]
2025-09-14 19:35:03,105 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 19:35:03,111 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1199 [INFO]: Iteration 100/100 (estimated time remaining: 2 minutes, 14 seconds)
2025-09-14 19:37:07,968 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1214 [DEBUG]: Evaluating for latency 24...
2025-09-14 19:37:16,939 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1221 [DEBUG]: Total Reward: 3659.40356 ± 1386.628
2025-09-14 19:37:16,940 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1222 [DEBUG]: All rewards: [np.float32(2126.2068), np.float32(4551.1216), np.float32(4636.0474), np.float32(4338.9155), np.float32(1316.291), np.float32(4600.3667), np.float32(1282.4121), np.float32(4720.9985), np.float32(4688.8843), np.float32(4332.7925)]
2025-09-14 19:37:16,940 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1223 [DEBUG]: All trajectory lengths: [np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0), np.float32(1000.0)]
2025-09-14 19:37:16,946 latency_env.delayed_mdp:training_loop(baseline-bpql-noisepromille50-halfcheetah):1251 [DEBUG]: Training session finished
