/Users/yunhaoyang/Desktop/prav-pres-rl/rl-starter-files/scripts/train.py --algo ppo --env MiniGrid-MultiRoom-N2-v00 --model mrv --frames 204800

Namespace(a=0, algo='ppo', batch_size=256, clip_eps=0.2, discount=0.99, entropy_coef=0.01, env='MiniGrid-MultiRoom-N2-v00', epochs=4, frames=204800, frames_per_proc=None, gae_lambda=0.95, k=0, log_interval=1, lr=0.001, max_grad_norm=0.5, mem=False, model='mrv', optim_alpha=0.99, optim_eps=1e-08, procs=16, recurrence=1, save_interval=10, seed=1, test=0, text=False, value_loss_coef=0.5)

Device: cpu

Environments loaded

Training status loaded

Observations preprocessor loaded
Model loaded

ACModel(
  (image_conv): Sequential(
    (0): Conv2d(3, 16, kernel_size=(2, 2), stride=(1, 1))
    (1): ReLU()
    (2): MaxPool2d(kernel_size=(2, 2), stride=(2, 2), padding=0, dilation=1, ceil_mode=False)
    (3): Conv2d(16, 32, kernel_size=(2, 2), stride=(1, 1))
    (4): ReLU()
    (5): Conv2d(32, 64, kernel_size=(2, 2), stride=(1, 1))
    (6): ReLU()
  )
  (actor): Sequential(
    (0): Linear(in_features=64, out_features=64, bias=True)
    (1): Tanh()
    (2): Linear(in_features=64, out_features=7, bias=True)
  )
  (critic): Sequential(
    (0): Linear(in_features=64, out_features=64, bias=True)
    (1): Tanh()
    (2): Linear(in_features=64, out_features=1, bias=True)
  )
)

Optimizer loaded

U 1 | F 002048 | FPS 3000 | D 0 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 0.0 0.0 0 0 | H 1.931 | V -0.082 | pL -0.017 | vL 0.001 | ∇ 0.022
U 2 | F 004096 | FPS 3070 | D 1 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.936 | V -0.071 | pL -0.025 | vL 0.000 | ∇ 0.015
U 3 | F 006144 | FPS 3194 | D 1 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.941 | V -0.053 | pL -0.009 | vL 0.000 | ∇ 0.005
U 4 | F 008192 | FPS 3154 | D 2 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.937 | V -0.044 | pL -0.013 | vL 0.000 | ∇ 0.007
U 5 | F 010240 | FPS 3121 | D 3 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.942 | V -0.033 | pL -0.012 | vL 0.000 | ∇ 0.006
U 6 | F 012288 | FPS 3137 | D 3 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.943 | V -0.027 | pL -0.005 | vL 0.000 | ∇ 0.002
U 7 | F 014336 | FPS 3106 | D 4 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.942 | V -0.020 | pL -0.006 | vL 0.000 | ∇ 0.003
U 8 | F 016384 | FPS 3132 | D 5 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.944 | V -0.014 | pL -0.005 | vL 0.000 | ∇ 0.003
U 9 | F 018432 | FPS 3077 | D 5 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.945 | V -0.011 | pL -0.001 | vL 0.000 | ∇ 0.002
U 10 | F 020480 | FPS 2877 | D 6 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.945 | V -0.009 | pL -0.003 | vL 0.000 | ∇ 0.002
Status saved
U 11 | F 022528 | FPS 3094 | D 7 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.945 | V -0.007 | pL -0.003 | vL 0.000 | ∇ 0.001
U 12 | F 024576 | FPS 3105 | D 7 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.945 | V -0.004 | pL -0.001 | vL 0.000 | ∇ 0.001
U 13 | F 026624 | FPS 2866 | D 8 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.945 | V -0.004 | pL -0.001 | vL 0.000 | ∇ 0.001
U 14 | F 028672 | FPS 2841 | D 9 | rR:μσmM 0.01 0.04 0.00 0.17 | F:μσmM 199.0 3.9 184.0 200.0 | H 1.944 | V -0.002 | pL -0.002 | vL 0.000 | ∇ 0.003
U 15 | F 030720 | FPS 2653 | D 10 | rR:μσmM 0.01 0.04 0.00 0.17 | F:μσmM 199.0 3.9 184.0 200.0 | H 1.945 | V -0.002 | pL -0.001 | vL 0.000 | ∇ 0.001
U 16 | F 032768 | FPS 3165 | D 10 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.945 | V -0.002 | pL -0.001 | vL 0.000 | ∇ 0.001
U 17 | F 034816 | FPS 2748 | D 11 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.946 | V -0.002 | pL -0.000 | vL 0.000 | ∇ 0.000
U 18 | F 036864 | FPS 2532 | D 12 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.946 | V -0.001 | pL -0.000 | vL 0.000 | ∇ 0.001
U 19 | F 038912 | FPS 2760 | D 13 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.945 | V -0.001 | pL -0.000 | vL 0.000 | ∇ 0.001
U 20 | F 040960 | FPS 2707 | D 13 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.946 | V -0.001 | pL -0.000 | vL 0.000 | ∇ 0.001
Status saved
U 21 | F 043008 | FPS 3056 | D 14 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.945 | V -0.001 | pL -0.000 | vL 0.000 | ∇ 0.001
U 22 | F 045056 | FPS 2897 | D 15 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.945 | V -0.001 | pL -0.000 | vL 0.000 | ∇ 0.001
U 23 | F 047104 | FPS 3084 | D 15 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.946 | V -0.001 | pL -0.000 | vL 0.000 | ∇ 0.001
U 24 | F 049152 | FPS 2958 | D 16 | rR:μσmM 0.02 0.07 0.00 0.28 | F:μσmM 197.5 9.7 160.0 200.0 | H 1.944 | V 0.000 | pL -0.002 | vL 0.000 | ∇ 0.005
U 25 | F 051200 | FPS 3159 | D 17 | rR:μσmM 0.02 0.10 0.00 0.39 | F:μσmM 195.9 15.7 135.0 200.0 | H 1.944 | V 0.001 | pL -0.004 | vL 0.000 | ∇ 0.005
U 26 | F 053248 | FPS 3091 | D 17 | rR:μσmM 0.02 0.10 0.00 0.39 | F:μσmM 195.9 15.7 135.0 200.0 | H 1.944 | V 0.000 | pL -0.000 | vL 0.000 | ∇ 0.002
U 27 | F 055296 | FPS 3038 | D 18 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.943 | V 0.003 | pL -0.000 | vL 0.000 | ∇ 0.004
U 28 | F 057344 | FPS 3041 | D 19 | rR:μσmM 0.05 0.18 0.00 0.74 | F:μσmM 191.1 34.6 57.0 200.0 | H 1.945 | V 0.001 | pL -0.001 | vL 0.000 | ∇ 0.003
U 29 | F 059392 | FPS 3118 | D 20 | rR:μσmM 0.04 0.14 0.00 0.57 | F:μσmM 193.5 25.2 96.0 200.0 | H 1.944 | V 0.005 | pL -0.005 | vL 0.000 | ∇ 0.007
U 30 | F 061440 | FPS 3071 | D 20 | rR:μσmM 0.04 0.14 0.00 0.57 | F:μσmM 193.5 25.2 96.0 200.0 | H 1.943 | V 0.001 | pL 0.000 | vL 0.000 | ∇ 0.002
Status saved
U 31 | F 063488 | FPS 3007 | D 21 | rR:μσmM 0.02 0.08 0.00 0.33 | F:μσmM 196.8 12.6 148.0 200.0 | H 1.941 | V 0.005 | pL -0.003 | vL 0.000 | ∇ 0.004
U 32 | F 065536 | FPS 2983 | D 22 | rR:μσmM 0.14 0.29 0.00 0.90 | F:μσmM 174.1 55.5 22.0 200.0 | H 1.943 | V 0.022 | pL -0.013 | vL 0.004 | ∇ 0.017
U 33 | F 067584 | FPS 2987 | D 22 | rR:μσmM 0.09 0.23 0.00 0.69 | F:μσmM 183.7 43.2 69.0 200.0 | H 1.938 | V 0.013 | pL -0.003 | vL 0.001 | ∇ 0.013
U 34 | F 069632 | FPS 2985 | D 23 | rR:μσmM 0.02 0.09 0.00 0.37 | F:μσmM 196.3 14.3 141.0 200.0 | H 1.940 | V 0.012 | pL -0.002 | vL 0.000 | ∇ 0.014
U 35 | F 071680 | FPS 2921 | D 24 | rR:μσmM 0.03 0.13 0.00 0.53 | F:μσmM 194.0 23.2 104.0 200.0 | H 1.939 | V 0.022 | pL -0.000 | vL 0.000 | ∇ 0.009
U 36 | F 073728 | FPS 3053 | D 24 | rR:μσmM 0.10 0.19 0.00 0.55 | F:μσmM 182.9 34.2 99.0 200.0 | H 1.935 | V 0.022 | pL -0.003 | vL 0.001 | ∇ 0.014
U 37 | F 075776 | FPS 3032 | D 25 | rR:μσmM 0.03 0.10 0.00 0.37 | F:μσmM 195.2 15.0 139.0 200.0 | H 1.939 | V 0.017 | pL 0.004 | vL 0.000 | ∇ 0.003
U 38 | F 077824 | FPS 3029 | D 26 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.941 | V 0.012 | pL 0.004 | vL 0.000 | ∇ 0.003
U 39 | F 079872 | FPS 3079 | D 26 | rR:μσmM 0.02 0.08 0.00 0.33 | F:μσmM 196.8 12.3 149.0 200.0 | H 1.942 | V 0.011 | pL -0.000 | vL 0.000 | ∇ 0.005
U 40 | F 081920 | FPS 3160 | D 27 | rR:μσmM 0.00 0.00 0.00 0.00 | F:μσmM 200.0 0.0 200.0 200.0 | H 1.944 | V 0.011 | pL 0.003 | vL 0.000 | ∇ 0.002
Status saved
U 41 | F 083968 | FPS 3150 | D 28 | rR:μσmM 0.02 0.06 0.00 0.26 | F:μσmM 197.8 8.5 165.0 200.0 | H 1.938 | V 0.017 | pL -0.000 | vL 0.000 | ∇ 0.009
U 42 | F 086016 | FPS 3125 | D 28 | rR:μσmM 0.11 0.24 0.00 0.88 | F:μσmM 181.3 45.7 26.0 200.0 | H 1.929 | V 0.026 | pL -0.010 | vL 0.002 | ∇ 0.017
U 43 | F 088064 | FPS 3127 | D 29 | rR:μσmM 0.33 0.36 0.00 0.87 | F:μσmM 137.0 68.9 30.0 200.0 | H 1.905 | V 0.099 | pL -0.036 | vL 0.008 | ∇ 0.043
U 44 | F 090112 | FPS 2934 | D 30 | rR:μσmM 0.28 0.34 0.00 0.91 | F:μσmM 149.6 65.8 20.0 200.0 | H 1.919 | V 0.048 | pL -0.007 | vL 0.004 | ∇ 0.023
U 45 | F 092160 | FPS 3068 | D 30 | rR:μσmM 0.12 0.24 0.00 0.91 | F:μσmM 180.0 45.7 20.0 200.0 | H 1.927 | V 0.034 | pL 0.001 | vL 0.001 | ∇ 0.013
U 46 | F 094208 | FPS 3078 | D 31 | rR:μσmM 0.05 0.12 0.00 0.37 | F:μσmM 192.0 19.0 139.0 200.0 | H 1.920 | V 0.042 | pL 0.002 | vL 0.001 | ∇ 0.013
U 47 | F 096256 | FPS 3058 | D 32 | rR:μσmM 0.09 0.12 0.00 0.34 | F:μσmM 188.5 17.8 146.0 200.0 | H 1.922 | V 0.044 | pL 0.001 | vL 0.001 | ∇ 0.009
U 48 | F 098304 | FPS 3112 | D 32 | rR:μσmM 0.12 0.15 0.00 0.52 | F:μσmM 183.0 25.1 106.0 200.0 | H 1.917 | V 0.040 | pL -0.000 | vL 0.001 | ∇ 0.014
U 49 | F 100352 | FPS 3051 | D 33 | rR:μσmM 0.16 0.23 0.00 0.82 | F:μσmM 173.8 43.4 41.0 200.0 | H 1.911 | V 0.061 | pL -0.011 | vL 0.004 | ∇ 0.035
U 50 | F 102400 | FPS 2922 | D 34 | rR:μσmM 0.29 0.34 0.00 0.82 | F:μσmM 145.8 65.0 39.0 200.0 | H 1.895 | V 0.064 | pL -0.015 | vL 0.004 | ∇ 0.024
Status saved
U 51 | F 104448 | FPS 3043 | D 34 | rR:μσmM 0.27 0.35 0.00 0.91 | F:μσmM 150.2 68.7 20.0 200.0 | H 1.908 | V 0.063 | pL -0.008 | vL 0.003 | ∇ 0.023
U 52 | F 106496 | FPS 3011 | D 35 | rR:μσmM 0.19 0.32 0.00 0.91 | F:μσmM 164.8 62.9 20.0 200.0 | H 1.910 | V 0.062 | pL -0.008 | vL 0.003 | ∇ 0.023
U 53 | F 108544 | FPS 3047 | D 36 | rR:μσmM 0.47 0.36 0.00 0.91 | F:μσmM 111.8 70.7 20.0 200.0 | H 1.859 | V 0.151 | pL -0.043 | vL 0.008 | ∇ 0.048
U 54 | F 110592 | FPS 2912 | D 36 | rR:μσmM 0.62 0.33 0.00 0.94 | F:μσmM 81.8 67.5 13.0 200.0 | H 1.819 | V 0.240 | pL -0.048 | vL 0.018 | ∇ 0.090
U 55 | F 112640 | FPS 3045 | D 37 | rR:μσmM 0.59 0.33 0.00 0.94 | F:μσmM 88.8 69.4 13.0 200.0 | H 1.874 | V 0.150 | pL -0.011 | vL 0.006 | ∇ 0.042
U 56 | F 114688 | FPS 2990 | D 38 | rR:μσmM 0.34 0.35 0.00 0.89 | F:μσmM 137.8 69.4 25.0 200.0 | H 1.895 | V 0.125 | pL 0.001 | vL 0.004 | ∇ 0.038
U 57 | F 116736 | FPS 2922 | D 39 | rR:μσmM 0.29 0.38 0.00 0.92 | F:μσmM 144.2 74.0 17.0 200.0 | H 1.855 | V 0.167 | pL 0.008 | vL 0.009 | ∇ 0.053
U 58 | F 118784 | FPS 2985 | D 39 | rR:μσmM 0.56 0.30 0.00 0.93 | F:μσmM 93.8 59.7 15.0 200.0 | H 1.773 | V 0.286 | pL -0.031 | vL 0.013 | ∇ 0.087
U 59 | F 120832 | FPS 2999 | D 40 | rR:μσmM 0.58 0.33 0.00 0.93 | F:μσmM 89.3 67.1 16.0 200.0 | H 1.806 | V 0.285 | pL -0.020 | vL 0.012 | ∇ 0.066
U 60 | F 122880 | FPS 3054 | D 41 | rR:μσmM 0.76 0.22 0.00 0.94 | F:μσmM 52.9 46.8 13.0 200.0 | H 1.752 | V 0.323 | pL -0.046 | vL 0.012 | ∇ 0.071
Status saved
U 61 | F 124928 | FPS 3083 | D 41 | rR:μσmM 0.64 0.29 0.00 0.92 | F:μσmM 76.6 59.1 18.0 200.0 | H 1.738 | V 0.356 | pL -0.057 | vL 0.012 | ∇ 0.090
U 62 | F 126976 | FPS 3044 | D 42 | rR:μσmM 0.73 0.18 0.00 0.91 | F:μσmM 59.9 37.3 19.0 200.0 | H 1.670 | V 0.462 | pL -0.052 | vL 0.010 | ∇ 0.065
U 63 | F 129024 | FPS 3065 | D 43 | rR:μσmM 0.72 0.19 0.00 0.93 | F:μσmM 61.6 39.1 16.0 200.0 | H 1.701 | V 0.431 | pL -0.004 | vL 0.008 | ∇ 0.064
U 64 | F 131072 | FPS 3024 | D 43 | rR:μσmM 0.69 0.26 0.00 0.95 | F:μσmM 66.8 54.5 11.0 200.0 | H 1.748 | V 0.409 | pL -0.002 | vL 0.012 | ∇ 0.072
U 65 | F 133120 | FPS 3058 | D 44 | rR:μσmM 0.66 0.26 0.00 0.93 | F:μσmM 74.3 53.9 15.0 200.0 | H 1.688 | V 0.430 | pL -0.003 | vL 0.010 | ∇ 0.066
U 66 | F 135168 | FPS 3015 | D 45 | rR:μσmM 0.62 0.27 0.00 0.91 | F:μσmM 82.4 55.3 19.0 200.0 | H 1.744 | V 0.369 | pL 0.015 | vL 0.006 | ∇ 0.053
U 67 | F 137216 | FPS 3025 | D 45 | rR:μσmM 0.71 0.24 0.00 0.94 | F:μσmM 64.5 50.4 14.0 200.0 | H 1.546 | V 0.487 | pL -0.038 | vL 0.010 | ∇ 0.080
U 68 | F 139264 | FPS 2993 | D 46 | rR:μσmM 0.81 0.12 0.32 0.95 | F:μσmM 41.5 26.1 12.0 150.0 | H 1.542 | V 0.525 | pL -0.047 | vL 0.009 | ∇ 0.067
U 69 | F 141312 | FPS 2968 | D 47 | rR:μσmM 0.84 0.13 0.21 0.95 | F:μσmM 36.7 28.6 11.0 175.0 | H 1.461 | V 0.605 | pL -0.048 | vL 0.009 | ∇ 0.075
U 70 | F 143360 | FPS 2958 | D 47 | rR:μσmM 0.85 0.14 0.00 0.95 | F:μσmM 32.4 29.0 10.0 200.0 | H 1.449 | V 0.639 | pL -0.022 | vL 0.008 | ∇ 0.058
Status saved
U 71 | F 145408 | FPS 2965 | D 48 | rR:μσmM 0.86 0.13 0.00 0.95 | F:μσmM 31.7 27.5 10.0 200.0 | H 1.395 | V 0.677 | pL -0.015 | vL 0.007 | ∇ 0.064
U 72 | F 147456 | FPS 2940 | D 49 | rR:μσmM 0.87 0.06 0.69 0.95 | F:μσmM 27.8 12.7 10.0 70.0 | H 1.402 | V 0.708 | pL -0.022 | vL 0.004 | ∇ 0.053
U 73 | F 149504 | FPS 2979 | D 49 | rR:μσmM 0.86 0.12 0.29 0.95 | F:μσmM 31.8 26.1 10.0 158.0 | H 1.450 | V 0.678 | pL 0.007 | vL 0.006 | ∇ 0.048
U 74 | F 151552 | FPS 2966 | D 50 | rR:μσmM 0.87 0.10 0.25 0.95 | F:μσmM 29.4 22.9 11.0 166.0 | H 1.447 | V 0.713 | pL -0.012 | vL 0.006 | ∇ 0.051
U 75 | F 153600 | FPS 2969 | D 51 | rR:μσmM 0.86 0.15 0.00 0.95 | F:μσmM 31.0 30.3 10.0 200.0 | H 1.481 | V 0.687 | pL 0.003 | vL 0.007 | ∇ 0.058
U 76 | F 155648 | FPS 2953 | D 52 | rR:μσmM 0.88 0.09 0.30 0.95 | F:μσmM 26.5 20.1 10.0 155.0 | H 1.456 | V 0.713 | pL -0.012 | vL 0.005 | ∇ 0.047
U 77 | F 157696 | FPS 2960 | D 52 | rR:μσmM 0.88 0.11 0.00 0.95 | F:μσmM 26.8 23.3 10.0 200.0 | H 1.389 | V 0.729 | pL -0.011 | vL 0.005 | ∇ 0.044
U 78 | F 159744 | FPS 2966 | D 53 | rR:μσmM 0.89 0.05 0.69 0.95 | F:μσmM 24.3 11.7 10.0 70.0 | H 1.359 | V 0.743 | pL -0.018 | vL 0.003 | ∇ 0.041
U 79 | F 161792 | FPS 2864 | D 54 | rR:μσmM 0.89 0.06 0.51 0.95 | F:μσmM 24.6 14.4 10.0 108.0 | H 1.368 | V 0.727 | pL -0.002 | vL 0.004 | ∇ 0.046
U 80 | F 163840 | FPS 2864 | D 54 | rR:μσmM 0.86 0.16 0.00 0.94 | F:μσmM 29.9 31.0 14.0 200.0 | H 1.424 | V 0.707 | pL 0.008 | vL 0.007 | ∇ 0.059
Status saved
U 81 | F 165888 | FPS 2964 | D 55 | rR:μσmM 0.86 0.13 0.20 0.95 | F:μσmM 31.2 29.1 10.0 177.0 | H 1.496 | V 0.690 | pL 0.013 | vL 0.007 | ∇ 0.053
U 82 | F 167936 | FPS 2960 | D 56 | rR:μσmM 0.86 0.12 0.10 0.95 | F:μσmM 31.7 27.4 11.0 200.0 | H 1.483 | V 0.696 | pL -0.004 | vL 0.006 | ∇ 0.056
U 83 | F 169984 | FPS 2738 | D 57 | rR:μσmM 0.86 0.08 0.46 0.95 | F:μσmM 31.1 17.1 11.0 121.0 | H 1.461 | V 0.705 | pL -0.014 | vL 0.003 | ∇ 0.038
U 84 | F 172032 | FPS 2729 | D 57 | rR:μσmM 0.86 0.07 0.62 0.95 | F:μσmM 30.4 14.7 12.0 84.0 | H 1.470 | V 0.702 | pL 0.003 | vL 0.003 | ∇ 0.038
U 85 | F 174080 | FPS 2748 | D 58 | rR:μσmM 0.86 0.11 0.20 0.95 | F:μσmM 30.9 23.6 12.0 178.0 | H 1.446 | V 0.702 | pL 0.008 | vL 0.004 | ∇ 0.038
U 86 | F 176128 | FPS 2833 | D 59 | rR:μσmM 0.85 0.09 0.37 0.96 | F:μσmM 33.8 20.5 9.0 141.0 | H 1.482 | V 0.688 | pL 0.009 | vL 0.005 | ∇ 0.049
U 87 | F 178176 | FPS 2737 | D 60 | rR:μσmM 0.86 0.08 0.38 0.95 | F:μσmM 30.2 18.7 11.0 137.0 | H 1.430 | V 0.714 | pL 0.002 | vL 0.003 | ∇ 0.040
U 88 | F 180224 | FPS 2721 | D 60 | rR:μσmM 0.86 0.08 0.54 0.95 | F:μσmM 30.9 18.5 10.0 102.0 | H 1.468 | V 0.681 | pL 0.005 | vL 0.003 | ∇ 0.035
U 89 | F 182272 | FPS 2903 | D 61 | rR:μσmM 0.86 0.14 0.00 0.95 | F:μσmM 31.2 28.6 11.0 200.0 | H 1.369 | V 0.714 | pL -0.017 | vL 0.005 | ∇ 0.043
U 90 | F 184320 | FPS 2954 | D 62 | rR:μσmM 0.86 0.08 0.63 0.95 | F:μσmM 32.0 16.8 11.0 82.0 | H 1.407 | V 0.701 | pL -0.004 | vL 0.003 | ∇ 0.041
Status saved
U 91 | F 186368 | FPS 2938 | D 62 | rR:μσmM 0.87 0.06 0.57 0.96 | F:μσmM 28.4 13.2 9.0 95.0 | H 1.371 | V 0.726 | pL -0.011 | vL 0.003 | ∇ 0.033
U 92 | F 188416 | FPS 2936 | D 63 | rR:μσmM 0.89 0.04 0.76 0.95 | F:μσmM 25.5 9.8 12.0 53.0 | H 1.368 | V 0.732 | pL -0.008 | vL 0.003 | ∇ 0.038
U 93 | F 190464 | FPS 2918 | D 64 | rR:μσmM 0.88 0.07 0.40 0.95 | F:μσmM 26.8 16.4 10.0 134.0 | H 1.312 | V 0.770 | pL -0.012 | vL 0.003 | ∇ 0.038
U 94 | F 192512 | FPS 2939 | D 64 | rR:μσmM 0.89 0.03 0.82 0.95 | F:μσmM 24.0 7.6 10.0 40.0 | H 1.348 | V 0.762 | pL -0.002 | vL 0.002 | ∇ 0.030
U 95 | F 194560 | FPS 2839 | D 65 | rR:μσmM 0.89 0.05 0.70 0.95 | F:μσmM 24.1 11.6 10.0 66.0 | H 1.322 | V 0.777 | pL -0.008 | vL 0.002 | ∇ 0.042
U 96 | F 196608 | FPS 2935 | D 66 | rR:μσmM 0.89 0.04 0.74 0.95 | F:μσmM 24.7 9.9 11.0 58.0 | H 1.423 | V 0.769 | pL 0.003 | vL 0.002 | ∇ 0.033
U 97 | F 198656 | FPS 2932 | D 67 | rR:μσmM 0.89 0.05 0.73 0.95 | F:μσmM 24.4 10.6 10.0 59.0 | H 1.398 | V 0.778 | pL 0.004 | vL 0.002 | ∇ 0.034
U 98 | F 200704 | FPS 2946 | D 67 | rR:μσmM 0.89 0.04 0.73 0.96 | F:μσmM 25.2 9.8 9.0 60.0 | H 1.388 | V 0.765 | pL 0.003 | vL 0.002 | ∇ 0.027
U 99 | F 202752 | FPS 2961 | D 68 | rR:μσmM 0.88 0.07 0.47 0.95 | F:μσmM 27.7 15.1 10.0 118.0 | H 1.479 | V 0.732 | pL 0.012 | vL 0.003 | ∇ 0.044
U 100 | F 204800 | FPS 2971 | D 69 | rR:μσmM 0.86 0.12 0.00 0.95 | F:μσmM 30.1 25.2 10.0 200.0 | H 1.516 | V 0.718 | pL 0.018 | vL 0.005 | ∇ 0.045
Status saved
/Users/yunhaoyang/Desktop/prav-pres-rl/rl-starter-files/scripts/train.py --algo ppo --env MiniGrid-MultiRoom-N2-v00 --model mrv --frames 307200

Namespace(a=0, algo='ppo', batch_size=256, clip_eps=0.2, discount=0.99, entropy_coef=0.01, env='MiniGrid-MultiRoom-N2-v00', epochs=4, frames=307200, frames_per_proc=None, gae_lambda=0.95, k=0, log_interval=1, lr=0.001, max_grad_norm=0.5, mem=False, model='mrv', optim_alpha=0.99, optim_eps=1e-08, procs=16, recurrence=1, save_interval=10, seed=1, test=0, text=False, value_loss_coef=0.5)

Device: cpu

Environments loaded

Training status loaded

Observations preprocessor loaded
Model loaded

ACModel(
  (image_conv): Sequential(
    (0): Conv2d(3, 16, kernel_size=(2, 2), stride=(1, 1))
    (1): ReLU()
    (2): MaxPool2d(kernel_size=(2, 2), stride=(2, 2), padding=0, dilation=1, ceil_mode=False)
    (3): Conv2d(16, 32, kernel_size=(2, 2), stride=(1, 1))
    (4): ReLU()
    (5): Conv2d(32, 64, kernel_size=(2, 2), stride=(1, 1))
    (6): ReLU()
  )
  (actor): Sequential(
    (0): Linear(in_features=64, out_features=64, bias=True)
    (1): Tanh()
    (2): Linear(in_features=64, out_features=7, bias=True)
  )
  (critic): Sequential(
    (0): Linear(in_features=64, out_features=64, bias=True)
    (1): Tanh()
    (2): Linear(in_features=64, out_features=1, bias=True)
  )
)

Optimizer loaded

U 101 | F 206848 | FPS 2848 | D 0 | rR:μσmM 0.85 0.07 0.67 0.94 | F:μσmM 34.1 14.9 14.0 73.0 | H 1.555 | V 0.687 | pL 0.017 | vL 0.003 | ∇ 0.039
U 102 | F 208896 | FPS 2701 | D 1 | rR:μσmM 0.84 0.08 0.57 0.94 | F:μσmM 35.8 17.7 14.0 96.0 | H 1.548 | V 0.668 | pL 0.007 | vL 0.003 | ∇ 0.041
U 103 | F 210944 | FPS 2812 | D 2 | rR:μσmM 0.77 0.14 0.38 0.91 | F:μσmM 50.6 30.3 19.0 138.0 | H 1.615 | V 0.614 | pL 0.037 | vL 0.005 | ∇ 0.053
U 104 | F 212992 | FPS 2799 | D 2 | rR:μσmM 0.75 0.20 0.00 0.94 | F:μσmM 55.2 42.1 14.0 200.0 | H 1.578 | V 0.609 | pL 0.025 | vL 0.007 | ∇ 0.063
U 105 | F 215040 | FPS 2964 | D 3 | rR:μσmM 0.85 0.07 0.51 0.95 | F:μσmM 34.2 15.9 11.0 109.0 | H 1.519 | V 0.668 | pL -0.022 | vL 0.004 | ∇ 0.038
U 106 | F 217088 | FPS 3026 | D 4 | rR:μσmM 0.86 0.09 0.43 0.95 | F:μσmM 31.3 20.2 10.0 126.0 | H 1.427 | V 0.709 | pL -0.013 | vL 0.004 | ∇ 0.043
U 107 | F 219136 | FPS 2760 | D 5 | rR:μσmM 0.89 0.04 0.69 0.95 | F:μσmM 23.7 9.8 10.0 68.0 | H 1.329 | V 0.769 | pL -0.024 | vL 0.002 | ∇ 0.038
U 108 | F 221184 | FPS 2910 | D 5 | rR:μσmM 0.90 0.04 0.78 0.95 | F:μσmM 22.3 8.4 10.0 49.0 | H 1.321 | V 0.773 | pL -0.019 | vL 0.002 | ∇ 0.031
U 109 | F 223232 | FPS 2963 | D 6 | rR:μσmM 0.89 0.06 0.64 0.96 | F:μσmM 24.6 12.8 9.0 81.0 | H 1.369 | V 0.765 | pL -0.003 | vL 0.002 | ∇ 0.027
U 110 | F 225280 | FPS 2940 | D 7 | rR:μσmM 0.89 0.07 0.55 0.95 | F:μσmM 23.6 15.3 10.0 101.0 | H 1.435 | V 0.752 | pL -0.000 | vL 0.003 | ∇ 0.036
Status saved
U 111 | F 227328 | FPS 2950 | D 7 | rR:μσmM 0.88 0.09 0.32 0.96 | F:μσmM 27.2 19.6 9.0 152.0 | H 1.468 | V 0.739 | pL 0.009 | vL 0.003 | ∇ 0.039
U 112 | F 229376 | FPS 2923 | D 8 | rR:μσmM 0.88 0.07 0.37 0.96 | F:μσmM 26.1 15.5 9.0 140.0 | H 1.474 | V 0.725 | pL 0.000 | vL 0.003 | ∇ 0.041
U 113 | F 231424 | FPS 2997 | D 9 | rR:μσmM 0.84 0.14 0.00 0.94 | F:μσmM 35.7 29.8 13.0 200.0 | H 1.494 | V 0.693 | pL 0.016 | vL 0.006 | ∇ 0.054
U 114 | F 233472 | FPS 3063 | D 9 | rR:μσmM 0.84 0.11 0.28 0.95 | F:μσmM 36.3 24.5 12.0 160.0 | H 1.478 | V 0.685 | pL 0.012 | vL 0.006 | ∇ 0.053
U 115 | F 235520 | FPS 2956 | D 10 | rR:μσmM 0.87 0.05 0.69 0.95 | F:μσmM 28.5 11.6 11.0 69.0 | H 1.427 | V 0.706 | pL -0.018 | vL 0.003 | ∇ 0.039
U 116 | F 237568 | FPS 2934 | D 11 | rR:μσmM 0.89 0.06 0.67 0.95 | F:μσmM 25.5 13.8 10.0 73.0 | H 1.333 | V 0.754 | pL -0.022 | vL 0.003 | ∇ 0.037
U 117 | F 239616 | FPS 2925 | D 12 | rR:μσmM 0.91 0.04 0.64 0.96 | F:μσmM 20.3 9.7 9.0 81.0 | H 1.255 | V 0.797 | pL -0.025 | vL 0.002 | ∇ 0.030
U 118 | F 241664 | FPS 2952 | D 12 | rR:μσmM 0.90 0.05 0.70 0.96 | F:μσmM 21.6 10.3 9.0 66.0 | H 1.353 | V 0.765 | pL 0.008 | vL 0.003 | ∇ 0.037
U 119 | F 243712 | FPS 2962 | D 13 | rR:μσmM 0.88 0.09 0.33 0.96 | F:μσmM 27.5 18.9 9.0 149.0 | H 1.365 | V 0.759 | pL 0.001 | vL 0.004 | ∇ 0.035
U 120 | F 245760 | FPS 2918 | D 14 | rR:μσmM 0.90 0.03 0.82 0.96 | F:μσmM 21.8 7.0 9.0 40.0 | H 1.346 | V 0.793 | pL -0.010 | vL 0.002 | ∇ 0.028
Status saved
U 121 | F 247808 | FPS 2912 | D 14 | rR:μσmM 0.90 0.04 0.68 0.95 | F:μσmM 21.1 9.8 10.0 72.0 | H 1.368 | V 0.796 | pL 0.002 | vL 0.002 | ∇ 0.029
U 122 | F 249856 | FPS 2919 | D 15 | rR:μσmM 0.89 0.07 0.57 0.95 | F:μσmM 24.2 15.3 10.0 96.0 | H 1.420 | V 0.777 | pL 0.021 | vL 0.003 | ∇ 0.037
U 123 | F 251904 | FPS 2951 | D 16 | rR:μσmM 0.89 0.04 0.78 0.95 | F:μσmM 23.5 8.9 10.0 49.0 | H 1.447 | V 0.755 | pL 0.004 | vL 0.002 | ∇ 0.029
U 124 | F 253952 | FPS 2970 | D 16 | rR:μσmM 0.87 0.08 0.48 0.95 | F:μσmM 27.9 17.3 11.0 116.0 | H 1.513 | V 0.729 | pL 0.019 | vL 0.004 | ∇ 0.047
U 125 | F 256000 | FPS 2996 | D 17 | rR:μσmM 0.83 0.18 0.00 0.95 | F:μσmM 37.5 36.3 10.0 200.0 | H 1.573 | V 0.664 | pL 0.027 | vL 0.006 | ∇ 0.056
U 126 | F 258048 | FPS 2977 | D 18 | rR:μσmM 0.84 0.13 0.00 0.95 | F:μσmM 34.1 27.1 10.0 200.0 | H 1.527 | V 0.696 | pL 0.003 | vL 0.004 | ∇ 0.043
U 127 | F 260096 | FPS 2992 | D 19 | rR:μσmM 0.85 0.07 0.62 0.95 | F:μσmM 33.6 15.8 10.0 84.0 | H 1.515 | V 0.710 | pL -0.003 | vL 0.003 | ∇ 0.031
U 128 | F 262144 | FPS 3025 | D 19 | rR:μσmM 0.87 0.05 0.73 0.95 | F:μσmM 29.1 11.6 12.0 60.0 | H 1.461 | V 0.730 | pL -0.008 | vL 0.002 | ∇ 0.028
U 129 | F 264192 | FPS 2989 | D 20 | rR:μσmM 0.86 0.07 0.66 0.95 | F:μσmM 30.5 14.4 11.0 76.0 | H 1.462 | V 0.718 | pL -0.000 | vL 0.003 | ∇ 0.034
U 130 | F 266240 | FPS 3006 | D 21 | rR:μσmM 0.87 0.06 0.66 0.95 | F:μσmM 28.1 13.7 11.0 75.0 | H 1.459 | V 0.711 | pL 0.000 | vL 0.002 | ∇ 0.028
Status saved
U 131 | F 268288 | FPS 2969 | D 21 | rR:μσmM 0.86 0.07 0.66 0.95 | F:μσmM 30.1 15.6 10.0 75.0 | H 1.438 | V 0.719 | pL 0.001 | vL 0.003 | ∇ 0.042
U 132 | F 270336 | FPS 2937 | D 22 | rR:μσmM 0.87 0.07 0.44 0.96 | F:μσmM 28.6 16.4 9.0 124.0 | H 1.414 | V 0.727 | pL -0.004 | vL 0.003 | ∇ 0.035
U 133 | F 272384 | FPS 2955 | D 23 | rR:μσmM 0.89 0.06 0.57 0.96 | F:μσmM 25.3 12.8 9.0 96.0 | H 1.363 | V 0.747 | pL -0.018 | vL 0.002 | ∇ 0.026
U 134 | F 274432 | FPS 2967 | D 23 | rR:μσmM 0.88 0.05 0.68 0.95 | F:μσmM 25.6 11.6 10.0 72.0 | H 1.372 | V 0.760 | pL -0.006 | vL 0.002 | ∇ 0.025
U 135 | F 276480 | FPS 2978 | D 24 | rR:μσmM 0.88 0.05 0.68 0.95 | F:μσmM 26.8 11.3 10.0 71.0 | H 1.332 | V 0.752 | pL 0.001 | vL 0.002 | ∇ 0.026
U 136 | F 278528 | FPS 2916 | D 25 | rR:μσmM 0.89 0.04 0.72 0.95 | F:μσmM 25.2 8.6 10.0 62.0 | H 1.386 | V 0.768 | pL -0.008 | vL 0.002 | ∇ 0.025
U 137 | F 280576 | FPS 2955 | D 25 | rR:μσmM 0.88 0.04 0.67 0.95 | F:μσmM 25.6 9.6 10.0 73.0 | H 1.449 | V 0.758 | pL 0.011 | vL 0.002 | ∇ 0.033
U 138 | F 282624 | FPS 2939 | D 26 | rR:μσmM 0.88 0.08 0.37 0.95 | F:μσmM 27.6 17.5 11.0 140.0 | H 1.494 | V 0.767 | pL 0.017 | vL 0.003 | ∇ 0.035
U 139 | F 284672 | FPS 2922 | D 27 | rR:μσmM 0.87 0.05 0.75 0.95 | F:μσmM 28.6 11.1 12.0 56.0 | H 1.485 | V 0.753 | pL 0.022 | vL 0.002 | ∇ 0.040
U 140 | F 286720 | FPS 2982 | D 28 | rR:μσmM 0.87 0.06 0.63 0.95 | F:μσmM 29.0 12.3 10.0 83.0 | H 1.535 | V 0.737 | pL 0.021 | vL 0.002 | ∇ 0.033
Status saved
U 141 | F 288768 | FPS 2988 | D 28 | rR:μσmM 0.85 0.07 0.53 0.95 | F:μσmM 33.3 16.4 10.0 105.0 | H 1.537 | V 0.715 | pL 0.015 | vL 0.003 | ∇ 0.040
U 142 | F 290816 | FPS 2969 | D 29 | rR:μσmM 0.85 0.07 0.52 0.96 | F:μσmM 33.2 15.8 9.0 107.0 | H 1.526 | V 0.695 | pL 0.009 | vL 0.003 | ∇ 0.036
U 143 | F 292864 | FPS 2978 | D 30 | rR:μσmM 0.85 0.07 0.66 0.95 | F:μσmM 33.9 16.1 12.0 75.0 | H 1.487 | V 0.685 | pL 0.000 | vL 0.003 | ∇ 0.039
U 144 | F 294912 | FPS 2956 | D 30 | rR:μσmM 0.87 0.06 0.68 0.95 | F:μσmM 29.2 14.0 10.0 72.0 | H 1.394 | V 0.707 | pL -0.027 | vL 0.003 | ∇ 0.034
U 145 | F 296960 | FPS 2925 | D 31 | rR:μσmM 0.89 0.05 0.77 0.96 | F:μσmM 23.9 10.9 9.0 51.0 | H 1.359 | V 0.746 | pL -0.031 | vL 0.003 | ∇ 0.043
U 146 | F 299008 | FPS 2916 | D 32 | rR:μσmM 0.89 0.04 0.76 0.95 | F:μσmM 24.8 9.9 10.0 54.0 | H 1.336 | V 0.753 | pL -0.007 | vL 0.002 | ∇ 0.032
U 147 | F 301056 | FPS 2953 | D 32 | rR:μσmM 0.89 0.07 0.38 0.96 | F:μσmM 25.4 15.8 9.0 137.0 | H 1.296 | V 0.765 | pL -0.010 | vL 0.003 | ∇ 0.029
U 148 | F 303104 | FPS 2930 | D 33 | rR:μσmM 0.90 0.04 0.65 0.95 | F:μσmM 21.4 8.6 10.0 77.0 | H 1.249 | V 0.793 | pL -0.012 | vL 0.002 | ∇ 0.024
U 149 | F 305152 | FPS 2908 | D 34 | rR:μσmM 0.90 0.04 0.73 0.96 | F:μσmM 21.5 8.7 9.0 59.0 | H 1.374 | V 0.796 | pL -0.001 | vL 0.001 | ∇ 0.024
U 150 | F 307200 | FPS 2957 | D 35 | rR:μσmM 0.90 0.04 0.73 0.95 | F:μσmM 22.6 9.2 10.0 61.0 | H 1.354 | V 0.785 | pL 0.010 | vL 0.002 | ∇ 0.030
Status saved
