How severe does this issue affect your experience of using Ray?
- High: It blocks me to complete my task.
Hi! I’m doing a multi-agent reinforcement learning task. I created a env with gymnasium. Each agent has a dict recording it’s status info. Here I want to return agent’s info after each episode. But I can’t find much introduction in offical document. I found a question with code :episode._last_infos[agent_id].
Is this kind callback method still avaviable? How can I find more detail? Thanks!