data/envs/atari/create_atari_dataset.py [89:107]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            normalized_obs = prepare_and_normalize_obs(actor_critic, obs)

            if not cfg.no_render:
                visualize_policy_inputs(normalized_obs)
            policy_outputs = actor_critic(normalized_obs, rnn_states)

            # sample actions from the distribution by default
            actions = policy_outputs["actions"]

            if cfg.eval_deterministic:
                action_distribution = actor_critic.action_distribution()
                actions = argmax_actions(action_distribution)

            # actions shape should be [num_agents, num_actions] even if it's [1, 1]
            if actions.ndim == 1:
                actions = unsqueeze_tensor(actions, dim=-1)
            actions = preprocess_actions(env_info, actions)

            rnn_states = policy_outputs["new_rnn_states"]
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



data/envs/mujoco/create_mujoco_dataset.py [154:172]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            normalized_obs = prepare_and_normalize_obs(actor_critic, obs)

            if not cfg.no_render:
                visualize_policy_inputs(normalized_obs)
            policy_outputs = actor_critic(normalized_obs, rnn_states)

            # sample actions from the distribution by default
            actions = policy_outputs["actions"]

            if cfg.eval_deterministic:
                action_distribution = actor_critic.action_distribution()
                actions = argmax_actions(action_distribution)

            # actions shape should be [num_agents, num_actions] even if it's [1, 1]
            if actions.ndim == 1:
                actions = unsqueeze_tensor(actions, dim=-1)
            actions = preprocess_actions(env_info, actions)

            rnn_states = policy_outputs["new_rnn_states"]
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -