['--alg', 'sac', '--env', 'HalfCheetah-v2', '--learn', 'baseline', '--traj', 'medium', '--seed', '0']
episode: 0 training return: tensor(-999.9949, device='cuda:0')
episode: 1 training return: tensor(-999.9916, device='cuda:0')
episode: 2 training return: tensor(-999.9839, device='cuda:0')
episode: 3 training return: tensor(-999.9965, device='cuda:0')
epoch: 1 test_true_pfm: -1.1560931042382787 sim_pfm: -999.9957014918327
episode: 4 training return: tensor(-999.9926, device='cuda:0')
episode: 5 training return: tensor(-999.9952, device='cuda:0')
episode: 6 training return: tensor(-999.9916, device='cuda:0')
episode: 7 training return: tensor(-999.9877, device='cuda:0')
epoch: 2 test_true_pfm: -0.15932908126710363 sim_pfm: -999.9954735636711
episode: 8 training return: tensor(-999.9899, device='cuda:0')
episode: 9 training return: tensor(-999.9935, device='cuda:0')
episode: 10 training return: tensor(-999.9931, device='cuda:0')
episode: 11 training return: tensor(-999.9902, device='cuda:0')
epoch: 3 test_true_pfm: -0.751839793230534 sim_pfm: -999.9954149325689
episode: 12 training return: tensor(-999.9951, device='cuda:0')
episode: 13 training return: tensor(-999.9971, device='cuda:0')
episode: 14 training return: tensor(-999.9968, device='cuda:0')
episode: 15 training return: tensor(-999.9886, device='cuda:0')
epoch: 4 test_true_pfm: -0.4114930365027265 sim_pfm: -999.9953603744507
episode: 16 training return: tensor(-999.9897, device='cuda:0')
episode: 17 training return: tensor(-999.9953, device='cuda:0')
episode: 18 training return: tensor(-999.9968, device='cuda:0')
episode: 19 training return: tensor(-999.8463, device='cuda:0')
epoch: 5 test_true_pfm: -0.3757823414090448 sim_pfm: -999.9954187472662
episode: 20 training return: tensor(-999.9812, device='cuda:0')
episode: 21 training return: tensor(-999.9895, device='cuda:0')
episode: 22 training return: tensor(-999.9956, device='cuda:0')
episode: 23 training return: tensor(-999.9814, device='cuda:0')
epoch: 6 test_true_pfm: -0.3479267425363828 sim_pfm: -999.9954153299332
