['--alg', 'sac', '--env', 'Swimmer-v3', '--learn', 'uncertainty', '--traj', 'medium', '--seed', '0', '--data', '100000']
episode: 0 training return: -481.0659505391135
episode: 1 training return: -463.02698430556893
episode: 2 training return: -414.885062578222
