rlkit/samplers/data_collector/step_collector.py [76:120]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        next_ob, reward, terminal, env_info = (
            self._env.step(action)
        )
        if self._render:
            self._env.render(**self._render_kwargs)
        terminal = np.array([terminal])
        reward = np.array([reward])
        # store path obs
        self._current_path_builder.add_all(
            observations=self._obs,
            actions=action,
            rewards=reward,
            next_observations=next_ob,
            terminals=terminal,
            agent_infos=agent_info,
            env_infos=env_info,
        )
        if terminal or len(self._current_path_builder) >= max_path_length:
            self._handle_rollout_ending(max_path_length,
                                        discard_incomplete_paths)
            self._start_new_rollout()
        else:
            self._obs = next_ob

    def _start_new_rollout(self):
        self._current_path_builder = PathBuilder()
        self._obs = self._env.reset()

    def _handle_rollout_ending(
            self,
            max_path_length,
            discard_incomplete_paths
    ):
        if len(self._current_path_builder) > 0:
            path = self._current_path_builder.get_all_stacked()
            path_len = len(path['actions'])
            if (
                    path_len != max_path_length
                    and not path['terminals'][-1]
                    and discard_incomplete_paths
            ):
                return
            self._epoch_paths.append(path)
            self._num_paths_total += 1
            self._num_steps_total += path_len
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



rlkit/samplers/data_collector/step_collector.py [206:250]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        next_ob, reward, terminal, env_info = (
            self._env.step(action)
        )
        if self._render:
            self._env.render(**self._render_kwargs)
        terminal = np.array([terminal])
        reward = np.array([reward])
        # store path obs
        self._current_path_builder.add_all(
            observations=self._obs,
            actions=action,
            rewards=reward,
            next_observations=next_ob,
            terminals=terminal,
            agent_infos=agent_info,
            env_infos=env_info,
        )
        if terminal or len(self._current_path_builder) >= max_path_length:
            self._handle_rollout_ending(max_path_length,
                                        discard_incomplete_paths)
            self._start_new_rollout()
        else:
            self._obs = next_ob

    def _start_new_rollout(self):
        self._current_path_builder = PathBuilder()
        self._obs = self._env.reset()

    def _handle_rollout_ending(
            self,
            max_path_length,
            discard_incomplete_paths
    ):
        if len(self._current_path_builder) > 0:
            path = self._current_path_builder.get_all_stacked()
            path_len = len(path['actions'])
            if (
                    path_len != max_path_length
                    and not path['terminals'][-1]
                    and discard_incomplete_paths
            ):
                return
            self._epoch_paths.append(path)
            self._num_paths_total += 1
            self._num_steps_total += path_len
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -