['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'baseline', '--traj', 'medium', '--seed', '0']
episode: 0 training return: tensor(-662.7651, device='cuda:0')
episode: 1 training return: tensor(-667.2327, device='cuda:0')
episode: 2 training return: tensor(-569.8550, device='cuda:0')
episode: 3 training return: tensor(-645.9119, device='cuda:0')
epoch: 1 test_true_pfm: -53.33091712699454 sim_pfm: -698.2181092699369
episode: 4 training return: tensor(-699.6844, device='cuda:0')
episode: 5 training return: tensor(-649.5691, device='cuda:0')
episode: 6 training return: tensor(-555.3438, device='cuda:0')
episode: 7 training return: tensor(-550.9752, device='cuda:0')
epoch: 2 test_true_pfm: -81.93551952323844 sim_pfm: -659.1329552829266
episode: 8 training return: tensor(-680.9412, device='cuda:0')
episode: 9 training return: tensor(-578.5676, device='cuda:0')
episode: 10 training return: tensor(-729.5076, device='cuda:0')
episode: 11 training return: tensor(-700.9161, device='cuda:0')
epoch: 3 test_true_pfm: 333.0371626917555 sim_pfm: -705.4813243593089
episode: 12 training return: tensor(-647.4778, device='cuda:0')
episode: 13 training return: tensor(-645.2949, device='cuda:0')
episode: 14 training return: tensor(-530.4552, device='cuda:0')
episode: 15 training return: tensor(-599.5447, device='cuda:0')
epoch: 4 test_true_pfm: -70.91545124925051 sim_pfm: -580.662673099277
episode: 16 training return: tensor(-621.4937, device='cuda:0')
episode: 17 training return: tensor(-507.9614, device='cuda:0')
episode: 18 training return: tensor(-663.7507, device='cuda:0')
episode: 19 training return: tensor(-744.4291, device='cuda:0')
epoch: 5 test_true_pfm: -28.268781411978097 sim_pfm: -494.1864394628598
episode: 20 training return: tensor(-661.7133, device='cuda:0')
episode: 21 training return: tensor(-389.4561, device='cuda:0')
episode: 22 training return: tensor(-513.8107, device='cuda:0')
