affordance_seg/collect_dset.py [158:193]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            current_episodes = self.envs.current_episodes()

            with torch.no_grad():
                (
                    _,
                    actions,
                    _,
                    test_recurrent_hidden_states,
                ) = self.actor_critic.act(
                    batch,
                    test_recurrent_hidden_states,
                    prev_actions,
                    not_done_masks,
                    deterministic=False,
                )

                prev_actions.copy_(actions)

            outputs = self.envs.step([a[0].item() for a in actions])

            observations, rewards, dones, infos = [
                list(x) for x in zip(*outputs)
            ]
            batch = self.batch_obs(observations, self.device)

            not_done_masks = torch.tensor(
                [[0.0] if done else [1.0] for done in dones],
                dtype=torch.float,
                device=self.device,
            )

            rewards = torch.tensor(
                rewards, dtype=torch.float, device=self.device
            ).unsqueeze(1)

            current_episode_reward += rewards
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



rl/ppo/ppo_trainer.py [541:576]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            current_episodes = self.envs.current_episodes()

            with torch.no_grad():
                (
                    _,
                    actions,
                    _,
                    test_recurrent_hidden_states,
                ) = self.actor_critic.act(
                    batch,
                    test_recurrent_hidden_states,
                    prev_actions,
                    not_done_masks,
                    deterministic=False,
                )

                prev_actions.copy_(actions)

            outputs = self.envs.step([a[0].item() for a in actions])

            observations, rewards, dones, infos = [
                list(x) for x in zip(*outputs)
            ]
            batch = self.batch_obs(observations, self.device)

            not_done_masks = torch.tensor(
                [[0.0] if done else [1.0] for done in dones],
                dtype=torch.float,
                device=self.device,
            )

            rewards = torch.tensor(
                rewards, dtype=torch.float, device=self.device
            ).unsqueeze(1)

            current_episode_reward += rewards
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -