❓ Question

When getting batches from a well-collected RecurrentRolloutBuffer, only episode_starts[batch_inds] will be returned to the sequence data. And this "episode_starts" is important for lstm policy to reset the hidden state during the training.
However, I have a question about the behavior here. As the seq_start_indices are decided together by both episode_starts and env_change, why are only episode_starts returned?
To be more clear, why the line 240 in common.recurrent.buffers is like "episode_starts=self.pad_and_flatten(self.episode_starts[batch_inds])" instead of "episode_starts=self.pad_and_flatten(self.episode_starts[batch_inds] or env_change[batch_inds])"?

Thank you for the explanation in advance.

Checklist

• I have checked that there is no similar issue in the repo
• I have read the documentation
• If code there is, it is minimal and working
• If code there is, it is formatted using the markdown code blocks for both code and stack traces.