['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'uncertainty', '--traj', 'expert', '--seed', '0', '--data', '100000']
episode: 0 training return: -1457.9627661667166
episode: 1 training return: -1450.8789203788294
episode: 2 training return: -1454.0119581225345
