['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'brac', '--traj', 'expert', '--seed', '0', '--data', '100000']
3106.2052761331606
episode: 0 training return: tensor(-597206.8750, device='cuda:0')
episode: 1 training return: tensor(-84881096., device='cuda:0')
episode: 2 training return: tensor(-48553228., device='cuda:0')
