validation loop not working for PPO

[laurenmoos]

actor_critic act method seems to be missing tobs from rollout storage

Traceback (most recent call last):
  File "main.py", line 108, in <module>
    main()
  File "main.py", line 104, in main
    agent_x.train(actor_critic, rollouts, envs, device)
  File "/home/lauren/weird-mario/MarioWM/a2c_ppo_acktr/agents/policy_gradient/policy_gradient.py", line 198, in train
    _validate(actor_critic, ob_rms, device)
  File "/home/lauren/weird-mario/MarioWM/a2c_ppo_acktr/agents/policy_gradient/policy_gradient.py", line 80, in _validate
    _, action, _, eval_recurrent_hidden_states = actor_critic.act(
TypeError: act() missing 1 required positional argument: 'masks'