['--alg', 'ddpg', '--env', 'Swimmer-v3', '--learn', 'brac', '--traj', 'medium', '--seed', '0', '--data', '100000']
57.495981164020236
episode: 0 training return: tensor(-1021663.6250, device='cuda:0')
episode: 1 training return: tensor(-799202.5000, device='cuda:0')
episode: 2 training return: tensor(-717368.8750, device='cuda:0')
episode: 3 training return: tensor(-853104.2500, device='cuda:0')
epoch: 1 test_true_pfm: 27.899361214755356
