How severe does this issue affect your experience of using Ray?
- Medium: It contributes to significant difficulty to complete my task, but I can work around it.
For a multiagent environment, The info returned requires to have same keys as the future observations as implemented in Ray 2.7 Multiagent checks for step function while in official Gymnasium documentation It states:
info (dict ) – Contains auxiliary diagnostic information (helpful for debugging, learning, and logging). This might, for instance, contain: metrics that describe the agent’s performance state, variables that are hidden from observations, or individual reward terms that are combined to produce the total reward.
Please align checks to official spec