lerobot/scripts/rl/learner.py [403:430]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            batch = next(online_iterator)

            if dataset_repo_id is not None:
                batch_offline = next(offline_iterator)
                batch = concatenate_batch_transitions(
                    left_batch_transitions=batch, right_batch_transition=batch_offline
                )

            actions = batch["action"]
            rewards = batch["reward"]
            observations = batch["state"]
            next_observations = batch["next_state"]
            done = batch["done"]
            check_nan_in_transition(observations=observations, actions=actions, next_state=next_observations)

            observation_features, next_observation_features = get_observation_features(
                policy=policy, observations=observations, next_observations=next_observations
            )

            # Create a batch dictionary with all required elements for the forward method
            forward_batch = {
                "action": actions,
                "reward": rewards,
                "state": observations,
                "next_state": next_observations,
                "done": done,
                "observation_feature": observation_features,
                "next_observation_feature": next_observation_features,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



lerobot/scripts/rl/learner.py [461:489]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        batch = next(online_iterator)

        if dataset_repo_id is not None:
            batch_offline = next(offline_iterator)
            batch = concatenate_batch_transitions(
                left_batch_transitions=batch, right_batch_transition=batch_offline
            )

        actions = batch["action"]
        rewards = batch["reward"]
        observations = batch["state"]
        next_observations = batch["next_state"]
        done = batch["done"]

        check_nan_in_transition(observations=observations, actions=actions, next_state=next_observations)

        observation_features, next_observation_features = get_observation_features(
            policy=policy, observations=observations, next_observations=next_observations
        )

        # Create a batch dictionary with all required elements for the forward method
        forward_batch = {
            "action": actions,
            "reward": rewards,
            "state": observations,
            "next_state": next_observations,
            "done": done,
            "observation_feature": observation_features,
            "next_observation_feature": next_observation_features,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -