['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'baseline', '--traj', 'expert', '--seed', '3']
episode: 0 training return: tensor(-743.7287, device='cuda:0')
episode: 1 training return: tensor(-897.4568, device='cuda:0')
episode: 2 training return: tensor(-674.8425, device='cuda:0')
episode: 3 training return: tensor(-767.1697, device='cuda:0')
epoch: 1 test_true_pfm: -16.222475436474678 sim_pfm: -926.9723785718282
episode: 4 training return: tensor(-790.7138, device='cuda:0')
episode: 5 training return: tensor(-810.0348, device='cuda:0')
episode: 6 training return: tensor(-800.0480, device='cuda:0')
episode: 7 training return: tensor(-790.7103, device='cuda:0')
epoch: 2 test_true_pfm: 159.52572436110006 sim_pfm: -978.202526593736
episode: 8 training return: tensor(-902.6746, device='cuda:0')
episode: 9 training return: tensor(-763.4977, device='cuda:0')
episode: 10 training return: tensor(-943.4206, device='cuda:0')
episode: 11 training return: tensor(-925.0837, device='cuda:0')
epoch: 3 test_true_pfm: 277.87558993213156 sim_pfm: -942.6082892911896
episode: 12 training return: tensor(-938.1396, device='cuda:0')
episode: 13 training return: tensor(-913.4238, device='cuda:0')
episode: 14 training return: tensor(-951.4478, device='cuda:0')
episode: 15 training return: tensor(-845.7509, device='cuda:0')
epoch: 4 test_true_pfm: 185.8756366230234 sim_pfm: -897.7742042959823
episode: 16 training return: tensor(-893.0876, device='cuda:0')
episode: 17 training return: tensor(-823.1479, device='cuda:0')
episode: 18 training return: tensor(-894.7886, device='cuda:0')
episode: 19 training return: tensor(-867.7930, device='cuda:0')
epoch: 5 test_true_pfm: 190.4338017578091 sim_pfm: -930.7281625136578
episode: 20 training return: tensor(-887.7660, device='cuda:0')
episode: 21 training return: tensor(-722.2186, device='cuda:0')
episode: 22 training return: tensor(-748.9720, device='cuda:0')
episode: 23 training return: tensor(-707.7234, device='cuda:0')
epoch: 6 test_true_pfm: -29.230485037473983 sim_pfm: -930.9971360783093
episode: 24 training return: tensor(-750.6421, device='cuda:0')
episode: 25 training return: tensor(-548.5718, device='cuda:0')
episode: 26 training return: tensor(-661.5885, device='cuda:0')
episode: 27 training return: tensor(-658.1359, device='cuda:0')
epoch: 7 test_true_pfm: -69.71543050279075 sim_pfm: -702.4922888354243
episode: 28 training return: tensor(-696.2266, device='cuda:0')
episode: 29 training return: tensor(-769.0480, device='cuda:0')
episode: 30 training return: tensor(-731.5825, device='cuda:0')
episode: 31 training return: tensor(-724.1447, device='cuda:0')
epoch: 8 test_true_pfm: 11.52905734604689 sim_pfm: -354.31107737030834
episode: 32 training return: tensor(-660.7992, device='cuda:0')
episode: 33 training return: tensor(-328.4056, device='cuda:0')
episode: 34 training return: tensor(-700.6190, device='cuda:0')
episode: 35 training return: tensor(-717.9753, device='cuda:0')
epoch: 9 test_true_pfm: -8.876082576772403 sim_pfm: -823.9319454987223
episode: 36 training return: tensor(-791.2379, device='cuda:0')
episode: 37 training return: tensor(-939.6028, device='cuda:0')
episode: 38 training return: tensor(-875.8919, device='cuda:0')
episode: 39 training return: tensor(-815.9582, device='cuda:0')
epoch: 10 test_true_pfm: 67.97231379093755 sim_pfm: -814.8687433237307
episode: 40 training return: tensor(-727.4938, device='cuda:0')
episode: 41 training return: tensor(-624.2829, device='cuda:0')
episode: 42 training return: tensor(-377.2437, device='cuda:0')
episode: 43 training return: tensor(-420.8456, device='cuda:0')
epoch: 11 test_true_pfm: 249.12480449784042 sim_pfm: -469.8462081660982
episode: 44 training return: tensor(-513.1795, device='cuda:0')
episode: 45 training return: tensor(-490.5453, device='cuda:0')
episode: 46 training return: tensor(-485.4637, device='cuda:0')
episode: 47 training return: tensor(-615.8275, device='cuda:0')
epoch: 12 test_true_pfm: -4.95800454507376 sim_pfm: -704.5668789297342
episode: 48 training return: tensor(-504.2371, device='cuda:0')
episode: 49 training return: tensor(-382.9923, device='cuda:0')
episode: 50 training return: tensor(-490.8565, device='cuda:0')
episode: 51 training return: tensor(-416.6261, device='cuda:0')
epoch: 13 test_true_pfm: 253.14962333525375 sim_pfm: -422.2504218094982
episode: 52 training return: tensor(-462.8935, device='cuda:0')
episode: 53 training return: tensor(-216.0252, device='cuda:0')
episode: 54 training return: tensor(-502.1467, device='cuda:0')
episode: 55 training return: tensor(-343.1133, device='cuda:0')
epoch: 14 test_true_pfm: 17.906589692696006 sim_pfm: -336.53914825152606
episode: 56 training return: tensor(-259.3319, device='cuda:0')
episode: 57 training return: tensor(-493.9156, device='cuda:0')
episode: 58 training return: tensor(-518.3755, device='cuda:0')
episode: 59 training return: tensor(-502.7283, device='cuda:0')
epoch: 15 test_true_pfm: 33.662627046114295 sim_pfm: -513.0010481952922
episode: 60 training return: tensor(-487.2249, device='cuda:0')
episode: 61 training return: tensor(-457.3754, device='cuda:0')
episode: 62 training return: tensor(-503.0739, device='cuda:0')
episode: 63 training return: tensor(-417.3558, device='cuda:0')
epoch: 16 test_true_pfm: -172.96088216425923 sim_pfm: -37.83992527995724
episode: 64 training return: tensor(-43.6499, device='cuda:0')
episode: 65 training return: tensor(-479.3177, device='cuda:0')
episode: 66 training return: tensor(-424.2577, device='cuda:0')
episode: 67 training return: tensor(-502.4493, device='cuda:0')
epoch: 17 test_true_pfm: 110.44634779692946 sim_pfm: -459.5689633876512
episode: 68 training return: tensor(-452.1834, device='cuda:0')
episode: 69 training return: tensor(-453.6671, device='cuda:0')
episode: 70 training return: tensor(-100.0398, device='cuda:0')
episode: 71 training return: tensor(-478.9788, device='cuda:0')
epoch: 18 test_true_pfm: 52.48880570524935 sim_pfm: -387.53767210493487
episode: 72 training return: tensor(-536.8641, device='cuda:0')
episode: 73 training return: tensor(-452.4066, device='cuda:0')
episode: 74 training return: tensor(-529.9841, device='cuda:0')
episode: 75 training return: tensor(-533.3121, device='cuda:0')
epoch: 19 test_true_pfm: 93.49350067388737 sim_pfm: -515.3543219630761
episode: 76 training return: tensor(-501.8761, device='cuda:0')
episode: 77 training return: tensor(-110.9198, device='cuda:0')
episode: 78 training return: tensor(-521.4903, device='cuda:0')
episode: 79 training return: tensor(-522.7385, device='cuda:0')
epoch: 20 test_true_pfm: 81.20259883092784 sim_pfm: -477.6509860339963
episode: 80 training return: tensor(-494.6468, device='cuda:0')
episode: 81 training return: tensor(-517.0609, device='cuda:0')
episode: 82 training return: tensor(-514.7134, device='cuda:0')
episode: 83 training return: tensor(-527.7117, device='cuda:0')
epoch: 21 test_true_pfm: 117.90893327975192 sim_pfm: -283.0278218012536
episode: 84 training return: tensor(-515.5388, device='cuda:0')
episode: 85 training return: tensor(-527.3247, device='cuda:0')
episode: 86 training return: tensor(-507.5762, device='cuda:0')
episode: 87 training return: tensor(-535.1942, device='cuda:0')
epoch: 22 test_true_pfm: 86.10837861745051 sim_pfm: -508.65088289558963
episode: 88 training return: tensor(-529.5645, device='cuda:0')
episode: 89 training return: tensor(-530.3665, device='cuda:0')
episode: 90 training return: tensor(-518.9491, device='cuda:0')
episode: 91 training return: tensor(-497.9778, device='cuda:0')
epoch: 23 test_true_pfm: 102.70878827124666 sim_pfm: -488.8951207964371
episode: 92 training return: tensor(-526.8498, device='cuda:0')
episode: 93 training return: tensor(-507.3901, device='cuda:0')
episode: 94 training return: tensor(-464.7823, device='cuda:0')
episode: 95 training return: tensor(-531.5426, device='cuda:0')
epoch: 24 test_true_pfm: 91.86169489147743 sim_pfm: -506.97520414444926
episode: 96 training return: tensor(-510.5287, device='cuda:0')
episode: 97 training return: tensor(-504.1742, device='cuda:0')
episode: 98 training return: tensor(-474.2834, device='cuda:0')
episode: 99 training return: tensor(-500.5294, device='cuda:0')
epoch: 25 test_true_pfm: 101.48558937522819 sim_pfm: -492.78741217777133
episode: 100 training return: tensor(-505.0908, device='cuda:0')
episode: 101 training return: tensor(-523.0638, device='cuda:0')
episode: 102 training return: tensor(-508.1362, device='cuda:0')
episode: 103 training return: tensor(-517.0661, device='cuda:0')
epoch: 26 test_true_pfm: 97.61213368379379 sim_pfm: -509.43263511514914
episode: 104 training return: tensor(263.3653, device='cuda:0')
episode: 105 training return: tensor(-505.6042, device='cuda:0')
episode: 106 training return: tensor(-442.5726, device='cuda:0')
episode: 107 training return: tensor(-443.3018, device='cuda:0')
epoch: 27 test_true_pfm: 84.65934612154805 sim_pfm: -514.9786755798074
episode: 108 training return: tensor(-101.1388, device='cuda:0')
episode: 109 training return: tensor(-458.2567, device='cuda:0')
episode: 110 training return: tensor(-509.5614, device='cuda:0')
episode: 111 training return: tensor(-517.0054, device='cuda:0')
epoch: 28 test_true_pfm: 91.22539433918273 sim_pfm: -509.0269075169538
episode: 112 training return: tensor(-521.9656, device='cuda:0')
episode: 113 training return: tensor(-503.7353, device='cuda:0')
episode: 114 training return: tensor(-511.1848, device='cuda:0')
episode: 115 training return: tensor(-140.9347, device='cuda:0')
epoch: 29 test_true_pfm: 98.56300771273823 sim_pfm: -500.82706295109045
episode: 116 training return: tensor(-497.8623, device='cuda:0')
episode: 117 training return: tensor(-514.5775, device='cuda:0')
episode: 118 training return: tensor(-450.0323, device='cuda:0')
episode: 119 training return: tensor(-515.4711, device='cuda:0')
epoch: 30 test_true_pfm: 112.2505826119645 sim_pfm: -496.52438757537556
episode: 120 training return: tensor(-519.6514, device='cuda:0')
episode: 121 training return: tensor(-432.9863, device='cuda:0')
episode: 122 training return: tensor(-509.1159, device='cuda:0')
episode: 123 training return: tensor(-512.5993, device='cuda:0')
epoch: 31 test_true_pfm: 91.43754808746705 sim_pfm: -511.0050252219662
episode: 124 training return: tensor(-518.7874, device='cuda:0')
episode: 125 training return: tensor(-518.5164, device='cuda:0')
episode: 126 training return: tensor(-513.9295, device='cuda:0')
episode: 127 training return: tensor(-521.6827, device='cuda:0')
epoch: 32 test_true_pfm: 93.04585768423597 sim_pfm: -506.5001213325498
episode: 128 training return: tensor(-426.5297, device='cuda:0')
episode: 129 training return: tensor(-506.2458, device='cuda:0')
episode: 130 training return: tensor(-464.0364, device='cuda:0')
episode: 131 training return: tensor(-7.5707, device='cuda:0')
epoch: 33 test_true_pfm: 87.49163416023687 sim_pfm: -512.77010365886
episode: 132 training return: tensor(-520.4795, device='cuda:0')
episode: 133 training return: tensor(-512.5778, device='cuda:0')
episode: 134 training return: tensor(-524.0218, device='cuda:0')
episode: 135 training return: tensor(-514.8834, device='cuda:0')
epoch: 34 test_true_pfm: 76.83330814584325 sim_pfm: -514.1945225354187
episode: 136 training return: tensor(-540.8995, device='cuda:0')
episode: 137 training return: tensor(-518.6109, device='cuda:0')
episode: 138 training return: tensor(-507.7423, device='cuda:0')
episode: 139 training return: tensor(-511.1352, device='cuda:0')
epoch: 35 test_true_pfm: 82.27497740530015 sim_pfm: -511.74740580446087
episode: 140 training return: tensor(-506.5629, device='cuda:0')
episode: 141 training return: tensor(-510.9488, device='cuda:0')
episode: 142 training return: tensor(-391.7063, device='cuda:0')
episode: 143 training return: tensor(-518.1468, device='cuda:0')
epoch: 36 test_true_pfm: 77.97458096783181 sim_pfm: -514.1564211435616
episode: 144 training return: tensor(-475.9088, device='cuda:0')
episode: 145 training return: tensor(-517.0162, device='cuda:0')
episode: 146 training return: tensor(-520.7834, device='cuda:0')
episode: 147 training return: tensor(-261.2830, device='cuda:0')
epoch: 37 test_true_pfm: 77.1248042318923 sim_pfm: -515.8347094727991
episode: 148 training return: tensor(-524.0062, device='cuda:0')
episode: 149 training return: tensor(-520.6571, device='cuda:0')
episode: 150 training return: tensor(-517.4858, device='cuda:0')
episode: 151 training return: tensor(-511.0796, device='cuda:0')
epoch: 38 test_true_pfm: 84.02821077320736 sim_pfm: -512.8165177367628
episode: 152 training return: tensor(-458.4307, device='cuda:0')
episode: 153 training return: tensor(-505.9446, device='cuda:0')
episode: 154 training return: tensor(-504.7143, device='cuda:0')
episode: 155 training return: tensor(-522.0143, device='cuda:0')
epoch: 39 test_true_pfm: 73.23774876946622 sim_pfm: -517.733787397854
episode: 156 training return: tensor(-496.8558, device='cuda:0')
episode: 157 training return: tensor(-515.0886, device='cuda:0')
episode: 158 training return: tensor(-516.3029, device='cuda:0')
episode: 159 training return: tensor(-499.3846, device='cuda:0')
epoch: 40 test_true_pfm: 83.18280062640603 sim_pfm: -514.0392607524991
episode: 160 training return: tensor(-440.4494, device='cuda:0')
episode: 161 training return: tensor(-511.8307, device='cuda:0')
episode: 162 training return: tensor(-351.1766, device='cuda:0')
episode: 163 training return: tensor(-462.1969, device='cuda:0')
epoch: 41 test_true_pfm: 74.80497748553809 sim_pfm: -515.1396430907771
episode: 164 training return: tensor(-341.4615, device='cuda:0')
episode: 165 training return: tensor(-522.1581, device='cuda:0')
episode: 166 training return: tensor(-504.2733, device='cuda:0')
episode: 167 training return: tensor(-505.0541, device='cuda:0')
epoch: 42 test_true_pfm: 79.62990888924031 sim_pfm: -511.41707875424373
episode: 168 training return: tensor(-512.4757, device='cuda:0')
episode: 169 training return: tensor(-442.8257, device='cuda:0')
episode: 170 training return: tensor(-518.8384, device='cuda:0')
episode: 171 training return: tensor(-509.5002, device='cuda:0')
epoch: 43 test_true_pfm: 78.70009934272444 sim_pfm: -515.4078734107316
episode: 172 training return: tensor(-467.1801, device='cuda:0')
episode: 173 training return: tensor(-513.9629, device='cuda:0')
episode: 174 training return: tensor(-513.5798, device='cuda:0')
episode: 175 training return: tensor(-455.9016, device='cuda:0')
epoch: 44 test_true_pfm: 79.44232151330456 sim_pfm: -515.746245034039
episode: 176 training return: tensor(-322.9561, device='cuda:0')
episode: 177 training return: tensor(-462.7648, device='cuda:0')
episode: 178 training return: tensor(-428.5388, device='cuda:0')
episode: 179 training return: tensor(-438.2207, device='cuda:0')
epoch: 45 test_true_pfm: 80.62158454087876 sim_pfm: -511.43456302270835
episode: 180 training return: tensor(-371.1335, device='cuda:0')
episode: 181 training return: tensor(-523.5236, device='cuda:0')
episode: 182 training return: tensor(-493.4580, device='cuda:0')
episode: 183 training return: tensor(-486.9828, device='cuda:0')
epoch: 46 test_true_pfm: 81.48605434402218 sim_pfm: -514.5786217946248
episode: 184 training return: tensor(-516.4254, device='cuda:0')
episode: 185 training return: tensor(-510.5840, device='cuda:0')
episode: 186 training return: tensor(-496.3511, device='cuda:0')
episode: 187 training return: tensor(-515.5447, device='cuda:0')
epoch: 47 test_true_pfm: 95.313385893165 sim_pfm: -504.64794235583395
episode: 188 training return: tensor(-504.4682, device='cuda:0')
episode: 189 training return: tensor(-500.6303, device='cuda:0')
episode: 190 training return: tensor(-506.6784, device='cuda:0')
episode: 191 training return: tensor(-497.6761, device='cuda:0')
epoch: 48 test_true_pfm: 80.59607896929667 sim_pfm: -512.4565874142572
episode: 192 training return: tensor(-530.1431, device='cuda:0')
episode: 193 training return: tensor(-514.4813, device='cuda:0')
episode: 194 training return: tensor(-498.7067, device='cuda:0')
episode: 195 training return: tensor(-506.4178, device='cuda:0')
epoch: 49 test_true_pfm: 85.62926921812446 sim_pfm: -509.791452724409
episode: 196 training return: tensor(-509.3212, device='cuda:0')
episode: 197 training return: tensor(-514.5012, device='cuda:0')
episode: 198 training return: tensor(-505.3962, device='cuda:0')
episode: 199 training return: tensor(-508.9008, device='cuda:0')
epoch: 50 test_true_pfm: 79.86004181835939 sim_pfm: -513.7721877628161
episode: 200 training return: tensor(-399.6555, device='cuda:0')
episode: 201 training return: tensor(-504.2073, device='cuda:0')
episode: 202 training return: tensor(-509.6882, device='cuda:0')
episode: 203 training return: tensor(-498.2669, device='cuda:0')
epoch: 51 test_true_pfm: 73.88398885113371 sim_pfm: -513.3758901017718
episode: 204 training return: tensor(-506.2464, device='cuda:0')
episode: 205 training return: tensor(-463.9582, device='cuda:0')
episode: 206 training return: tensor(-320.2737, device='cuda:0')
episode: 207 training return: tensor(-472.5225, device='cuda:0')
epoch: 52 test_true_pfm: 79.08526808576865 sim_pfm: -515.3025391907431
episode: 208 training return: tensor(-513.7058, device='cuda:0')
episode: 209 training return: tensor(-505.6960, device='cuda:0')
episode: 210 training return: tensor(-497.6163, device='cuda:0')
episode: 211 training return: tensor(-434.5055, device='cuda:0')
epoch: 53 test_true_pfm: 94.20813490915407 sim_pfm: -508.6133326090251
episode: 212 training return: tensor(-513.0266, device='cuda:0')
episode: 213 training return: tensor(-506.0655, device='cuda:0')
episode: 214 training return: tensor(-505.1086, device='cuda:0')
episode: 215 training return: tensor(-503.1342, device='cuda:0')
epoch: 54 test_true_pfm: 97.45262633974916 sim_pfm: -503.6352033186704
episode: 216 training return: tensor(-507.1185, device='cuda:0')
episode: 217 training return: tensor(-501.6752, device='cuda:0')
episode: 218 training return: tensor(-503.1792, device='cuda:0')
episode: 219 training return: tensor(-506.2407, device='cuda:0')
epoch: 55 test_true_pfm: 77.36187247629378 sim_pfm: -513.9602200904241
episode: 220 training return: tensor(-428.7212, device='cuda:0')
episode: 221 training return: tensor(-507.6771, device='cuda:0')
episode: 222 training return: tensor(-510.5896, device='cuda:0')
episode: 223 training return: tensor(-510.2733, device='cuda:0')
epoch: 56 test_true_pfm: 90.05611842370007 sim_pfm: -507.23595384228975
episode: 224 training return: tensor(-501.8891, device='cuda:0')
episode: 225 training return: tensor(-445.1396, device='cuda:0')
episode: 226 training return: tensor(-439.2673, device='cuda:0')
episode: 227 training return: tensor(-504.3778, device='cuda:0')
epoch: 57 test_true_pfm: 82.35107075901045 sim_pfm: -511.7541050238845
episode: 228 training return: tensor(-470.5865, device='cuda:0')
episode: 229 training return: tensor(-420.8412, device='cuda:0')
episode: 230 training return: tensor(-460.9753, device='cuda:0')
episode: 231 training return: tensor(-421.7063, device='cuda:0')
epoch: 58 test_true_pfm: 76.51629595206383 sim_pfm: -512.6948913809223
episode: 232 training return: tensor(-426.7483, device='cuda:0')
episode: 233 training return: tensor(-437.7505, device='cuda:0')
episode: 234 training return: tensor(-513.2901, device='cuda:0')
episode: 235 training return: tensor(-508.2206, device='cuda:0')
epoch: 59 test_true_pfm: 88.70202646427917 sim_pfm: -504.10575931395095
episode: 236 training return: tensor(-508.0751, device='cuda:0')
episode: 237 training return: tensor(-498.5535, device='cuda:0')
episode: 238 training return: tensor(-497.4892, device='cuda:0')
episode: 239 training return: tensor(-503.1728, device='cuda:0')
epoch: 60 test_true_pfm: 98.03923193236864 sim_pfm: -499.34316880628467
episode: 240 training return: tensor(-489.9110, device='cuda:0')
episode: 241 training return: tensor(-495.1015, device='cuda:0')
episode: 242 training return: tensor(-522.7596, device='cuda:0')
episode: 243 training return: tensor(-495.0641, device='cuda:0')
epoch: 61 test_true_pfm: 81.71089926300328 sim_pfm: -507.22909471640986
episode: 244 training return: tensor(-506.5285, device='cuda:0')
episode: 245 training return: tensor(-415.2588, device='cuda:0')
episode: 246 training return: tensor(-498.8880, device='cuda:0')
episode: 247 training return: tensor(-499.0586, device='cuda:0')
epoch: 62 test_true_pfm: 77.78828497755029 sim_pfm: -512.3304340809894
episode: 248 training return: tensor(-495.4448, device='cuda:0')
episode: 249 training return: tensor(-441.1023, device='cuda:0')
episode: 250 training return: tensor(-431.9245, device='cuda:0')
episode: 251 training return: tensor(-495.6947, device='cuda:0')
epoch: 63 test_true_pfm: 81.29477733429883 sim_pfm: -502.1850552732746
episode: 252 training return: tensor(-403.3979, device='cuda:0')
episode: 253 training return: tensor(-493.4838, device='cuda:0')
episode: 254 training return: tensor(-501.2356, device='cuda:0')
episode: 255 training return: tensor(-498.5265, device='cuda:0')
epoch: 64 test_true_pfm: 91.1952775062316 sim_pfm: -505.1773119804954
episode: 256 training return: tensor(-340.1378, device='cuda:0')
episode: 257 training return: tensor(-497.8212, device='cuda:0')
episode: 258 training return: tensor(-503.9261, device='cuda:0')
episode: 259 training return: tensor(-502.4919, device='cuda:0')
epoch: 65 test_true_pfm: 90.52662286086895 sim_pfm: -500.46620856722194
episode: 260 training return: tensor(-401.5520, device='cuda:0')
episode: 261 training return: tensor(-503.0669, device='cuda:0')
episode: 262 training return: tensor(-499.9966, device='cuda:0')
episode: 263 training return: tensor(-411.7730, device='cuda:0')
epoch: 66 test_true_pfm: 85.54761805686131 sim_pfm: -505.0916922154526
episode: 264 training return: tensor(-513.9855, device='cuda:0')
episode: 265 training return: tensor(-408.0195, device='cuda:0')
episode: 266 training return: tensor(-438.9011, device='cuda:0')
episode: 267 training return: tensor(-510.6575, device='cuda:0')
epoch: 67 test_true_pfm: 80.25067787358218 sim_pfm: -504.5536755695939
episode: 268 training return: tensor(-446.9882, device='cuda:0')
episode: 269 training return: tensor(-502.4526, device='cuda:0')
episode: 270 training return: tensor(-500.2884, device='cuda:0')
episode: 271 training return: tensor(-469.3706, device='cuda:0')
epoch: 68 test_true_pfm: 77.82080088106459 sim_pfm: -506.9403815942351
episode: 272 training return: tensor(-438.8397, device='cuda:0')
episode: 273 training return: tensor(-498.6028, device='cuda:0')
episode: 274 training return: tensor(-491.3932, device='cuda:0')
episode: 275 training return: tensor(-503.9883, device='cuda:0')
epoch: 69 test_true_pfm: 82.1147823179926 sim_pfm: -506.19707238441333
episode: 276 training return: tensor(-512.1873, device='cuda:0')
episode: 277 training return: tensor(-454.0739, device='cuda:0')
episode: 278 training return: tensor(-428.9491, device='cuda:0')
episode: 279 training return: tensor(-495.2017, device='cuda:0')
epoch: 70 test_true_pfm: 78.4380851068244 sim_pfm: -506.31057307807106
episode: 280 training return: tensor(-443.5344, device='cuda:0')
episode: 281 training return: tensor(-496.5795, device='cuda:0')
episode: 282 training return: tensor(-510.9568, device='cuda:0')
episode: 283 training return: tensor(-458.0972, device='cuda:0')
epoch: 71 test_true_pfm: 86.76022941561466 sim_pfm: -511.06955932138953
episode: 284 training return: tensor(-502.1570, device='cuda:0')
episode: 285 training return: tensor(-492.1166, device='cuda:0')
episode: 286 training return: tensor(-501.1974, device='cuda:0')
episode: 287 training return: tensor(-445.2558, device='cuda:0')
epoch: 72 test_true_pfm: 82.99991206186097 sim_pfm: -501.38289321955136
episode: 288 training return: tensor(-454.5204, device='cuda:0')
episode: 289 training return: tensor(-428.3181, device='cuda:0')
episode: 290 training return: tensor(-511.7870, device='cuda:0')
episode: 291 training return: tensor(-494.6111, device='cuda:0')
epoch: 73 test_true_pfm: 85.81424579530547 sim_pfm: -503.0250507745853
episode: 292 training return: tensor(-502.3800, device='cuda:0')
episode: 293 training return: tensor(-506.0686, device='cuda:0')
episode: 294 training return: tensor(-497.1343, device='cuda:0')
episode: 295 training return: tensor(-493.3184, device='cuda:0')
epoch: 74 test_true_pfm: 80.32549646462614 sim_pfm: -503.3080285207058
episode: 296 training return: tensor(-495.8261, device='cuda:0')
episode: 297 training return: tensor(-425.5644, device='cuda:0')
episode: 298 training return: tensor(-488.8360, device='cuda:0')
episode: 299 training return: tensor(-501.9575, device='cuda:0')
epoch: 75 test_true_pfm: 94.16945723753206 sim_pfm: -494.90215253457427
episode: 300 training return: tensor(-400.8402, device='cuda:0')
episode: 301 training return: tensor(-456.9399, device='cuda:0')
episode: 302 training return: tensor(-500.5663, device='cuda:0')
episode: 303 training return: tensor(-447.0029, device='cuda:0')
epoch: 76 test_true_pfm: 84.21768972743838 sim_pfm: -496.7957466393709
episode: 304 training return: tensor(-488.7518, device='cuda:0')
episode: 305 training return: tensor(-502.6297, device='cuda:0')
episode: 306 training return: tensor(-465.2938, device='cuda:0')
episode: 307 training return: tensor(-504.3276, device='cuda:0')
epoch: 77 test_true_pfm: 91.25004226825199 sim_pfm: -500.617163569259
episode: 308 training return: tensor(-496.0370, device='cuda:0')
episode: 309 training return: tensor(-425.0983, device='cuda:0')
episode: 310 training return: tensor(-505.6878, device='cuda:0')
episode: 311 training return: tensor(-496.9272, device='cuda:0')
epoch: 78 test_true_pfm: 80.96841554727138 sim_pfm: -507.2975644823746
episode: 312 training return: tensor(-497.8675, device='cuda:0')
episode: 313 training return: tensor(-500.8823, device='cuda:0')
episode: 314 training return: tensor(-454.6445, device='cuda:0')
episode: 315 training return: tensor(-492.6893, device='cuda:0')
epoch: 79 test_true_pfm: 79.41337235938116 sim_pfm: -509.2552727051079
episode: 316 training return: tensor(-494.5817, device='cuda:0')
episode: 317 training return: tensor(-433.5203, device='cuda:0')
episode: 318 training return: tensor(-497.7026, device='cuda:0')
episode: 319 training return: tensor(-493.9162, device='cuda:0')
epoch: 80 test_true_pfm: 93.86401092138226 sim_pfm: -499.8111751017471
episode: 320 training return: tensor(-499.2731, device='cuda:0')
episode: 321 training return: tensor(-494.7769, device='cuda:0')
episode: 322 training return: tensor(-499.3908, device='cuda:0')
episode: 323 training return: tensor(-500.4124, device='cuda:0')
epoch: 81 test_true_pfm: 97.73657920156063 sim_pfm: -499.55366466155584
episode: 324 training return: tensor(-503.3175, device='cuda:0')
episode: 325 training return: tensor(-491.9887, device='cuda:0')
episode: 326 training return: tensor(-489.7649, device='cuda:0')
episode: 327 training return: tensor(-483.8306, device='cuda:0')
epoch: 82 test_true_pfm: 99.65383037987904 sim_pfm: -490.2607321647617
episode: 328 training return: tensor(-492.6156, device='cuda:0')
episode: 329 training return: tensor(-501.5952, device='cuda:0')
episode: 330 training return: tensor(-404.5748, device='cuda:0')
episode: 331 training return: tensor(-376.0564, device='cuda:0')
epoch: 83 test_true_pfm: 94.44848017765874 sim_pfm: -490.71492916345596
episode: 332 training return: tensor(-405.1557, device='cuda:0')
episode: 333 training return: tensor(-494.8619, device='cuda:0')
episode: 334 training return: tensor(-487.3224, device='cuda:0')
episode: 335 training return: tensor(-487.7286, device='cuda:0')
epoch: 84 test_true_pfm: 95.37849755924401 sim_pfm: -490.4136632476002
episode: 336 training return: tensor(-491.2072, device='cuda:0')
episode: 337 training return: tensor(-485.2948, device='cuda:0')
episode: 338 training return: tensor(-494.7852, device='cuda:0')
episode: 339 training return: tensor(-485.4330, device='cuda:0')
epoch: 85 test_true_pfm: 94.57457532923264 sim_pfm: -495.78348011585575
episode: 340 training return: tensor(-395.1180, device='cuda:0')
episode: 341 training return: tensor(-475.5181, device='cuda:0')
episode: 342 training return: tensor(-425.9158, device='cuda:0')
episode: 343 training return: tensor(-485.0124, device='cuda:0')
epoch: 86 test_true_pfm: 93.05799569683909 sim_pfm: -498.720634486371
episode: 344 training return: tensor(-419.5514, device='cuda:0')
episode: 345 training return: tensor(-481.8800, device='cuda:0')
episode: 346 training return: tensor(-414.2523, device='cuda:0')
episode: 347 training return: tensor(-487.2749, device='cuda:0')
epoch: 87 test_true_pfm: 101.18367690077285 sim_pfm: -497.7482329569757
episode: 348 training return: tensor(-491.1869, device='cuda:0')
episode: 349 training return: tensor(-496.7529, device='cuda:0')
episode: 350 training return: tensor(-491.8997, device='cuda:0')
episode: 351 training return: tensor(-498.1324, device='cuda:0')
epoch: 88 test_true_pfm: 108.0931092313532 sim_pfm: -482.74910743006814
episode: 352 training return: tensor(-456.6367, device='cuda:0')
episode: 353 training return: tensor(-391.2725, device='cuda:0')
episode: 354 training return: tensor(-505.5715, device='cuda:0')
episode: 355 training return: tensor(-403.3005, device='cuda:0')
epoch: 89 test_true_pfm: 78.68707552334575 sim_pfm: -501.20059579246055
episode: 356 training return: tensor(-422.3883, device='cuda:0')
episode: 357 training return: tensor(-395.2770, device='cuda:0')
episode: 358 training return: tensor(-467.6692, device='cuda:0')
episode: 359 training return: tensor(-478.7750, device='cuda:0')
epoch: 90 test_true_pfm: 83.40310594100221 sim_pfm: -498.07265378317487
episode: 360 training return: tensor(-487.9235, device='cuda:0')
episode: 361 training return: tensor(-410.6409, device='cuda:0')
episode: 362 training return: tensor(-406.0561, device='cuda:0')
episode: 363 training return: tensor(-484.5188, device='cuda:0')
epoch: 91 test_true_pfm: 97.8170038210169 sim_pfm: -487.7139570241173
episode: 364 training return: tensor(-475.4263, device='cuda:0')
episode: 365 training return: tensor(-418.4685, device='cuda:0')
episode: 366 training return: tensor(-425.1203, device='cuda:0')
episode: 367 training return: tensor(-498.9475, device='cuda:0')
epoch: 92 test_true_pfm: 105.31374640214659 sim_pfm: -493.26958685616654
episode: 368 training return: tensor(-442.7550, device='cuda:0')
episode: 369 training return: tensor(-389.9678, device='cuda:0')
episode: 370 training return: tensor(-494.3229, device='cuda:0')
episode: 371 training return: tensor(-436.5962, device='cuda:0')
epoch: 93 test_true_pfm: 103.66645963560978 sim_pfm: -487.6529086008668
episode: 372 training return: tensor(-400.7156, device='cuda:0')
episode: 373 training return: tensor(-479.8409, device='cuda:0')
episode: 374 training return: tensor(-458.7819, device='cuda:0')
episode: 375 training return: tensor(-391.9662, device='cuda:0')
epoch: 94 test_true_pfm: 97.33890458109666 sim_pfm: -491.5241995925705
episode: 376 training return: tensor(-464.6153, device='cuda:0')
episode: 377 training return: tensor(-458.8559, device='cuda:0')
episode: 378 training return: tensor(-359.2277, device='cuda:0')
episode: 379 training return: tensor(-397.6998, device='cuda:0')
epoch: 95 test_true_pfm: 136.2393094396469 sim_pfm: -474.56420548118575
episode: 380 training return: tensor(-411.5274, device='cuda:0')
episode: 381 training return: tensor(-403.8819, device='cuda:0')
episode: 382 training return: tensor(-371.5253, device='cuda:0')
episode: 383 training return: tensor(-478.2185, device='cuda:0')
epoch: 96 test_true_pfm: 93.46147787243505 sim_pfm: -485.9914400738974
episode: 384 training return: tensor(-478.8303, device='cuda:0')
episode: 385 training return: tensor(-368.4197, device='cuda:0')
episode: 386 training return: tensor(-406.0819, device='cuda:0')
episode: 387 training return: tensor(-411.4519, device='cuda:0')
epoch: 97 test_true_pfm: 87.05594421195678 sim_pfm: -494.28229224619764
episode: 388 training return: tensor(-465.9975, device='cuda:0')
episode: 389 training return: tensor(-415.0344, device='cuda:0')
episode: 390 training return: tensor(-330.1825, device='cuda:0')
episode: 391 training return: tensor(-345.8805, device='cuda:0')
epoch: 98 test_true_pfm: 148.6275367957894 sim_pfm: -456.23774850865203
episode: 392 training return: tensor(-383.3875, device='cuda:0')
episode: 393 training return: tensor(-337.6376, device='cuda:0')
episode: 394 training return: tensor(-274.6492, device='cuda:0')
episode: 395 training return: tensor(-261.8686, device='cuda:0')
epoch: 99 test_true_pfm: 387.94416258623033 sim_pfm: -327.8745610123442
episode: 396 training return: tensor(-296.0548, device='cuda:0')
episode: 397 training return: tensor(-311.7083, device='cuda:0')
episode: 398 training return: tensor(-257.9010, device='cuda:0')
episode: 399 training return: tensor(-338.3686, device='cuda:0')
epoch: 100 test_true_pfm: 472.66370165842847 sim_pfm: -244.5630220551975
episode: 400 training return: tensor(-345.2740, device='cuda:0')
episode: 401 training return: tensor(-329.1944, device='cuda:0')
episode: 402 training return: tensor(-293.2701, device='cuda:0')
episode: 403 training return: tensor(-200.8222, device='cuda:0')
epoch: 101 test_true_pfm: 356.5803126427552 sim_pfm: -327.4229218347464
episode: 404 training return: tensor(-222.9646, device='cuda:0')
episode: 405 training return: tensor(-212.8023, device='cuda:0')
episode: 406 training return: tensor(-305.8020, device='cuda:0')
episode: 407 training return: tensor(-257.0984, device='cuda:0')
epoch: 102 test_true_pfm: 524.5295149573118 sim_pfm: -215.90489322366193
episode: 408 training return: tensor(-224.1883, device='cuda:0')
episode: 409 training return: tensor(-205.2328, device='cuda:0')
episode: 410 training return: tensor(-244.6053, device='cuda:0')
episode: 411 training return: tensor(-353.2960, device='cuda:0')
epoch: 103 test_true_pfm: 553.2130647352411 sim_pfm: -177.64249293415924
episode: 412 training return: tensor(-271.4850, device='cuda:0')
episode: 413 training return: tensor(-220.2822, device='cuda:0')
episode: 414 training return: tensor(-276.9619, device='cuda:0')
episode: 415 training return: tensor(-207.4797, device='cuda:0')
epoch: 104 test_true_pfm: 432.12372432643923 sim_pfm: -227.76469489953402
episode: 416 training return: tensor(-135.7880, device='cuda:0')
episode: 417 training return: tensor(-253.0633, device='cuda:0')
episode: 418 training return: tensor(-211.8344, device='cuda:0')
episode: 419 training return: tensor(-231.5018, device='cuda:0')
epoch: 105 test_true_pfm: 430.84622015339534 sim_pfm: -259.9860454928712
episode: 420 training return: tensor(-251.4869, device='cuda:0')
episode: 421 training return: tensor(-187.3671, device='cuda:0')
episode: 422 training return: tensor(-181.0653, device='cuda:0')
episode: 423 training return: tensor(-203.2156, device='cuda:0')
epoch: 106 test_true_pfm: 478.0276381181429 sim_pfm: -272.1299676503889
episode: 424 training return: tensor(-228.9597, device='cuda:0')
episode: 425 training return: tensor(-267.2968, device='cuda:0')
episode: 426 training return: tensor(-208.7702, device='cuda:0')
episode: 427 training return: tensor(-158.7028, device='cuda:0')
epoch: 107 test_true_pfm: 503.38917491371876 sim_pfm: -243.17566159162865
episode: 428 training return: tensor(-292.4782, device='cuda:0')
episode: 429 training return: tensor(-178.6735, device='cuda:0')
episode: 430 training return: tensor(-158.6681, device='cuda:0')
episode: 431 training return: tensor(-174.3185, device='cuda:0')
epoch: 108 test_true_pfm: 659.3926013147028 sim_pfm: -140.3209415607465
episode: 432 training return: tensor(-216.1561, device='cuda:0')
episode: 433 training return: tensor(-99.5995, device='cuda:0')
episode: 434 training return: tensor(-122.3885, device='cuda:0')
episode: 435 training return: tensor(-185.7070, device='cuda:0')
epoch: 109 test_true_pfm: 788.9824440356433 sim_pfm: -9.671421830775216
episode: 436 training return: tensor(-143.6720, device='cuda:0')
episode: 437 training return: tensor(-105.8814, device='cuda:0')
episode: 438 training return: tensor(-96.2468, device='cuda:0')
episode: 439 training return: tensor(-72.4721, device='cuda:0')
epoch: 110 test_true_pfm: 826.9018889961471 sim_pfm: -19.705002438674757
episode: 440 training return: tensor(-72.4061, device='cuda:0')
episode: 441 training return: tensor(-182.4355, device='cuda:0')
episode: 442 training return: tensor(-53.4610, device='cuda:0')
episode: 443 training return: tensor(-126.4372, device='cuda:0')
epoch: 111 test_true_pfm: 886.4327314671312 sim_pfm: 27.64225721192391
episode: 444 training return: tensor(-49.2119, device='cuda:0')
episode: 445 training return: tensor(-126.5979, device='cuda:0')
episode: 446 training return: tensor(-186.5041, device='cuda:0')
episode: 447 training return: tensor(-72.2809, device='cuda:0')
epoch: 112 test_true_pfm: 810.6230779854641 sim_pfm: 19.42377270537933
episode: 448 training return: tensor(-123.4259, device='cuda:0')
episode: 449 training return: tensor(-95.2706, device='cuda:0')
episode: 450 training return: tensor(-32.9957, device='cuda:0')
episode: 451 training return: tensor(-118.4597, device='cuda:0')
epoch: 113 test_true_pfm: 882.700847473031 sim_pfm: 8.525898176051365
episode: 452 training return: tensor(-72.2867, device='cuda:0')
episode: 453 training return: tensor(-117.5787, device='cuda:0')
episode: 454 training return: tensor(-40.5672, device='cuda:0')
episode: 455 training return: tensor(-110.2420, device='cuda:0')
epoch: 114 test_true_pfm: 922.3087646525336 sim_pfm: 42.46180487265034
episode: 456 training return: tensor(-128.1264, device='cuda:0')
episode: 457 training return: tensor(-145.0185, device='cuda:0')
episode: 458 training return: tensor(-130.1600, device='cuda:0')
episode: 459 training return: tensor(-219.0367, device='cuda:0')
epoch: 115 test_true_pfm: 899.3564687058589 sim_pfm: -4.095631590190654
episode: 460 training return: tensor(-129.2285, device='cuda:0')
episode: 461 training return: tensor(-77.1537, device='cuda:0')
episode: 462 training return: tensor(-145.2626, device='cuda:0')
episode: 463 training return: tensor(-134.0499, device='cuda:0')
epoch: 116 test_true_pfm: 916.8823696386552 sim_pfm: 34.75744209609305
episode: 464 training return: tensor(-66.7885, device='cuda:0')
episode: 465 training return: tensor(-78.3175, device='cuda:0')
episode: 466 training return: tensor(-92.4232, device='cuda:0')
episode: 467 training return: tensor(-77.3308, device='cuda:0')
epoch: 117 test_true_pfm: 849.4088924447433 sim_pfm: -22.98546960102006
episode: 468 training return: tensor(-82.5891, device='cuda:0')
episode: 469 training return: tensor(-83.1871, device='cuda:0')
episode: 470 training return: tensor(-45.9459, device='cuda:0')
episode: 471 training return: tensor(-84.4776, device='cuda:0')
epoch: 118 test_true_pfm: 960.496657572946 sim_pfm: 58.195470043225214
episode: 472 training return: tensor(-97.4096, device='cuda:0')
episode: 473 training return: tensor(-89.8552, device='cuda:0')
episode: 474 training return: tensor(-76.4736, device='cuda:0')
episode: 475 training return: tensor(-114.2071, device='cuda:0')
epoch: 119 test_true_pfm: 774.0575903114556 sim_pfm: -76.20214231170637
episode: 476 training return: tensor(-67.8033, device='cuda:0')
episode: 477 training return: tensor(-29.7837, device='cuda:0')
episode: 478 training return: tensor(-67.9300, device='cuda:0')
episode: 479 training return: tensor(-88.2147, device='cuda:0')
epoch: 120 test_true_pfm: 888.1443098071877 sim_pfm: 8.070972636846514
episode: 480 training return: tensor(-87.3033, device='cuda:0')
episode: 481 training return: tensor(-45.7739, device='cuda:0')
episode: 482 training return: tensor(-38.8197, device='cuda:0')
episode: 483 training return: tensor(-89.8817, device='cuda:0')
epoch: 121 test_true_pfm: 765.1858846763188 sim_pfm: -73.6773372287086
episode: 484 training return: tensor(-49.9843, device='cuda:0')
episode: 485 training return: tensor(-133.9712, device='cuda:0')
episode: 486 training return: tensor(-108.9049, device='cuda:0')
episode: 487 training return: tensor(-106.6365, device='cuda:0')
epoch: 122 test_true_pfm: 744.8268742671038 sim_pfm: -95.39058062195545
episode: 488 training return: tensor(-84.0197, device='cuda:0')
episode: 489 training return: tensor(-65.4778, device='cuda:0')
episode: 490 training return: tensor(-126.9100, device='cuda:0')
episode: 491 training return: tensor(-76.1521, device='cuda:0')
epoch: 123 test_true_pfm: 852.4160539018922 sim_pfm: -20.924527949964006
episode: 492 training return: tensor(-85.9458, device='cuda:0')
episode: 493 training return: tensor(-31.8400, device='cuda:0')
episode: 494 training return: tensor(-84.4540, device='cuda:0')
episode: 495 training return: tensor(-61.1725, device='cuda:0')
epoch: 124 test_true_pfm: 789.7014033462459 sim_pfm: -79.05634146614466
episode: 496 training return: tensor(-108.5229, device='cuda:0')
episode: 497 training return: tensor(-121.7765, device='cuda:0')
episode: 498 training return: tensor(-50.7826, device='cuda:0')
episode: 499 training return: tensor(-32.1049, device='cuda:0')
epoch: 125 test_true_pfm: 777.5303140876343 sim_pfm: -76.295523041316
episode: 500 training return: tensor(-11.3493, device='cuda:0')
episode: 501 training return: tensor(-24.1119, device='cuda:0')
episode: 502 training return: tensor(-67.0368, device='cuda:0')
episode: 503 training return: tensor(-42.6988, device='cuda:0')
epoch: 126 test_true_pfm: 785.9021998805747 sim_pfm: -60.48564300043896
episode: 504 training return: tensor(-101.7413, device='cuda:0')
episode: 505 training return: tensor(-104.5782, device='cuda:0')
episode: 506 training return: tensor(-53.3708, device='cuda:0')
episode: 507 training return: tensor(-35.5861, device='cuda:0')
epoch: 127 test_true_pfm: 879.603024130273 sim_pfm: -1.279451169471334
episode: 508 training return: tensor(-9.5719, device='cuda:0')
episode: 509 training return: tensor(-28.6201, device='cuda:0')
episode: 510 training return: tensor(-64.1994, device='cuda:0')
episode: 511 training return: tensor(-48.2786, device='cuda:0')
epoch: 128 test_true_pfm: 838.0491615079109 sim_pfm: -46.51061656838283
episode: 512 training return: tensor(-49.8877, device='cuda:0')
episode: 513 training return: tensor(-8.2175, device='cuda:0')
episode: 514 training return: tensor(-61.9028, device='cuda:0')
episode: 515 training return: tensor(60.1191, device='cuda:0')
epoch: 129 test_true_pfm: 934.9889702967206 sim_pfm: 47.58984528656583
episode: 516 training return: tensor(-35.5736, device='cuda:0')
episode: 517 training return: tensor(-58.5586, device='cuda:0')
episode: 518 training return: tensor(-39.4696, device='cuda:0')
episode: 519 training return: tensor(-54.9585, device='cuda:0')
epoch: 130 test_true_pfm: 944.32289536277 sim_pfm: 42.21568158078784
episode: 520 training return: tensor(-31.9916, device='cuda:0')
episode: 521 training return: tensor(-36.8726, device='cuda:0')
episode: 522 training return: tensor(-27.3606, device='cuda:0')
episode: 523 training return: tensor(-24.9711, device='cuda:0')
epoch: 131 test_true_pfm: 1001.3899585854928 sim_pfm: 67.68056134029757
episode: 524 training return: tensor(-3.0210, device='cuda:0')
episode: 525 training return: tensor(-41.2307, device='cuda:0')
episode: 526 training return: tensor(-13.8959, device='cuda:0')
episode: 527 training return: tensor(45.9102, device='cuda:0')
epoch: 132 test_true_pfm: 958.7315918386436 sim_pfm: 54.996187279447135
episode: 528 training return: tensor(-59.2252, device='cuda:0')
episode: 529 training return: tensor(-18.6892, device='cuda:0')
episode: 530 training return: tensor(8.1573, device='cuda:0')
episode: 531 training return: tensor(-10.8083, device='cuda:0')
epoch: 133 test_true_pfm: 1010.6613847591492 sim_pfm: 104.11677454167511
episode: 532 training return: tensor(-39.8551, device='cuda:0')
episode: 533 training return: tensor(-28.7347, device='cuda:0')
episode: 534 training return: tensor(-55.7710, device='cuda:0')
episode: 535 training return: tensor(1.0079, device='cuda:0')
epoch: 134 test_true_pfm: 1020.6235849750029 sim_pfm: 96.2933548828684
episode: 536 training return: tensor(-8.4743, device='cuda:0')
episode: 537 training return: tensor(-26.1292, device='cuda:0')
episode: 538 training return: tensor(-35.2697, device='cuda:0')
episode: 539 training return: tensor(-9.5612, device='cuda:0')
epoch: 135 test_true_pfm: 1025.6179797477546 sim_pfm: 114.3316399670827
episode: 540 training return: tensor(6.1470, device='cuda:0')
episode: 541 training return: tensor(-25.8232, device='cuda:0')
episode: 542 training return: tensor(-17.8449, device='cuda:0')
episode: 543 training return: tensor(2.9773, device='cuda:0')
epoch: 136 test_true_pfm: 937.5165225415235 sim_pfm: 47.17070931434864
episode: 544 training return: tensor(-61.4809, device='cuda:0')
episode: 545 training return: tensor(-14.2815, device='cuda:0')
episode: 546 training return: tensor(-20.1500, device='cuda:0')
episode: 547 training return: tensor(54.3838, device='cuda:0')
epoch: 137 test_true_pfm: 971.8570482178199 sim_pfm: 80.09955393951775
episode: 548 training return: tensor(-42.4746, device='cuda:0')
episode: 549 training return: tensor(-26.0487, device='cuda:0')
episode: 550 training return: tensor(-67.6589, device='cuda:0')
episode: 551 training return: tensor(21.9069, device='cuda:0')
epoch: 138 test_true_pfm: 977.379559817075 sim_pfm: 73.8410778917217
episode: 552 training return: tensor(-18.2686, device='cuda:0')
episode: 553 training return: tensor(-19.5359, device='cuda:0')
episode: 554 training return: tensor(-47.1483, device='cuda:0')
episode: 555 training return: tensor(12.0841, device='cuda:0')
epoch: 139 test_true_pfm: 932.7740482697169 sim_pfm: 41.85753351279224
episode: 556 training return: tensor(18.9666, device='cuda:0')
episode: 557 training return: tensor(5.7831, device='cuda:0')
episode: 558 training return: tensor(-0.1342, device='cuda:0')
episode: 559 training return: tensor(6.2638, device='cuda:0')
epoch: 140 test_true_pfm: 1014.6186258959574 sim_pfm: 96.97316990752006
episode: 560 training return: tensor(-35.1078, device='cuda:0')
episode: 561 training return: tensor(-20.4392, device='cuda:0')
episode: 562 training return: tensor(0.6869, device='cuda:0')
episode: 563 training return: tensor(14.2209, device='cuda:0')
epoch: 141 test_true_pfm: 989.0864308928932 sim_pfm: 82.45537335243232
episode: 564 training return: tensor(-34.9641, device='cuda:0')
episode: 565 training return: tensor(12.7065, device='cuda:0')
episode: 566 training return: tensor(13.2081, device='cuda:0')
episode: 567 training return: tensor(-0.5149, device='cuda:0')
epoch: 142 test_true_pfm: 966.3720756061599 sim_pfm: 59.051531505897096
episode: 568 training return: tensor(-13.4574, device='cuda:0')
episode: 569 training return: tensor(-25.5529, device='cuda:0')
episode: 570 training return: tensor(-9.8359, device='cuda:0')
episode: 571 training return: tensor(-32.3775, device='cuda:0')
epoch: 143 test_true_pfm: 974.2756496436123 sim_pfm: 53.26432942971587
episode: 572 training return: tensor(-0.6251, device='cuda:0')
episode: 573 training return: tensor(-16.7187, device='cuda:0')
episode: 574 training return: tensor(19.9465, device='cuda:0')
episode: 575 training return: tensor(-42.4295, device='cuda:0')
epoch: 144 test_true_pfm: 880.0293291539783 sim_pfm: 1.0796288755179073
episode: 576 training return: tensor(-22.4216, device='cuda:0')
episode: 577 training return: tensor(-4.3929, device='cuda:0')
episode: 578 training return: tensor(28.8719, device='cuda:0')
episode: 579 training return: tensor(29.3829, device='cuda:0')
epoch: 145 test_true_pfm: 1029.5587702921111 sim_pfm: 106.71661988180131
episode: 580 training return: tensor(6.4932, device='cuda:0')
episode: 581 training return: tensor(34.3162, device='cuda:0')
episode: 582 training return: tensor(21.6346, device='cuda:0')
episode: 583 training return: tensor(6.2105, device='cuda:0')
epoch: 146 test_true_pfm: 966.2012728512091 sim_pfm: 60.854723924751546
episode: 584 training return: tensor(-0.6141, device='cuda:0')
episode: 585 training return: tensor(0.8016, device='cuda:0')
episode: 586 training return: tensor(0.9730, device='cuda:0')
episode: 587 training return: tensor(23.0143, device='cuda:0')
epoch: 147 test_true_pfm: 991.4469288469444 sim_pfm: 77.52355633621725
episode: 588 training return: tensor(18.6562, device='cuda:0')
episode: 589 training return: tensor(27.7820, device='cuda:0')
episode: 590 training return: tensor(-30.3609, device='cuda:0')
episode: 591 training return: tensor(30.3573, device='cuda:0')
epoch: 148 test_true_pfm: 965.6836137014984 sim_pfm: 60.48904115136247
episode: 592 training return: tensor(30.1993, device='cuda:0')
episode: 593 training return: tensor(39.1325, device='cuda:0')
episode: 594 training return: tensor(34.4657, device='cuda:0')
episode: 595 training return: tensor(35.9303, device='cuda:0')
epoch: 149 test_true_pfm: 954.2701627624698 sim_pfm: 51.44914595678953
episode: 596 training return: tensor(8.6329, device='cuda:0')
episode: 597 training return: tensor(27.8156, device='cuda:0')
episode: 598 training return: tensor(-7.1261, device='cuda:0')
episode: 599 training return: tensor(26.0896, device='cuda:0')
epoch: 150 test_true_pfm: 1010.7152367299117 sim_pfm: 85.40218126496377
