['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'baseline', '--traj', 'medium', '--seed', '0']
episode: 0 training return: tensor(-369.4145, device='cuda:0')
episode: 1 training return: tensor(-624.5062, device='cuda:0')
episode: 2 training return: tensor(-583.6329, device='cuda:0')
episode: 3 training return: tensor(-440.1349, device='cuda:0')
epoch: 1 test_true_pfm: 382.8245869122136 sim_pfm: -567.1627613214272
episode: 4 training return: tensor(-482.9557, device='cuda:0')
episode: 5 training return: tensor(-266.1811, device='cuda:0')
episode: 6 training return: tensor(-504.1799, device='cuda:0')
episode: 7 training return: tensor(-563.3619, device='cuda:0')
epoch: 2 test_true_pfm: 37.28656542682922 sim_pfm: -573.5204556219591
episode: 8 training return: tensor(-406.7379, device='cuda:0')
episode: 9 training return: tensor(-483.1520, device='cuda:0')
episode: 10 training return: tensor(-143.4052, device='cuda:0')
episode: 11 training return: tensor(-353.9209, device='cuda:0')
epoch: 3 test_true_pfm: -75.800776287975 sim_pfm: -375.034064173388
episode: 12 training return: tensor(-593.8605, device='cuda:0')
episode: 13 training return: tensor(-837.6511, device='cuda:0')
episode: 14 training return: tensor(-563.6424, device='cuda:0')
episode: 15 training return: tensor(-597.5178, device='cuda:0')
epoch: 4 test_true_pfm: 120.15002121114186 sim_pfm: -540.0242738635765
episode: 16 training return: tensor(-779.5660, device='cuda:0')
episode: 17 training return: tensor(-657.1991, device='cuda:0')
episode: 18 training return: tensor(-748.6865, device='cuda:0')
episode: 19 training return: tensor(-734.6013, device='cuda:0')
epoch: 5 test_true_pfm: 37.76269949650468 sim_pfm: -743.7471024212427
episode: 20 training return: tensor(-571.9414, device='cuda:0')
episode: 21 training return: tensor(-737.6985, device='cuda:0')
episode: 22 training return: tensor(-855.4547, device='cuda:0')
episode: 23 training return: tensor(-864.6555, device='cuda:0')
epoch: 6 test_true_pfm: 212.59865773587623 sim_pfm: -873.2290266976343
