interaction_exploration/viz_trainer.py [88:109]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.actor_critic = self.agent.actor_critic

        observations = self.envs.reset()
        batch = self.batch_obs(observations, self.device)

        current_episode_reward = torch.zeros(
            self.envs.num_envs, 1, device=self.device
        )

        test_recurrent_hidden_states = torch.zeros(
            self.actor_critic.net.num_recurrent_layers,
            self.config.NUM_PROCESSES,
            ppo_cfg.hidden_size,
            device=self.device,
        )
        prev_actions = torch.zeros(
            self.config.NUM_PROCESSES, 1, device=self.device, dtype=torch.long
        )
        not_done_masks = torch.zeros(
            self.config.NUM_PROCESSES, 1, device=self.device
        )
        stats_episodes = dict()  
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



rl/ppo/ppo_trainer.py [499:520]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.actor_critic = self.agent.actor_critic

        observations = self.envs.reset()
        batch = self.batch_obs(observations, self.device)

        current_episode_reward = torch.zeros(
            self.envs.num_envs, 1, device=self.device
        )

        test_recurrent_hidden_states = torch.zeros(
            self.actor_critic.net.num_recurrent_layers,
            self.config.NUM_PROCESSES,
            ppo_cfg.hidden_size,
            device=self.device,
        )
        prev_actions = torch.zeros(
            self.config.NUM_PROCESSES, 1, device=self.device, dtype=torch.long
        )
        not_done_masks = torch.zeros(
            self.config.NUM_PROCESSES, 1, device=self.device
        )
        stats_episodes = dict()  # dict of dicts that stores stats per episode
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -