You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
We found that in the 4ag RWARE task, env.reward_spec().generate_value() gives something of shape (), but the reward that environment outputs is actually of shape (num_agents).
This is curious because I believe the scenario should output a reward of shape ().
Maybe it's a wrapper thing?
The text was updated successfully, but these errors were encountered:
Thanks Louise looks like this is a bug, we duplicated the reward and discount but never update the specs, my vote is to just not duplicate it and add a dummy agent dim so everything behaves the same.
We found that in the 4ag RWARE task, env.reward_spec().generate_value() gives something of shape (), but the reward that environment outputs is actually of shape (num_agents).
This is curious because I believe the scenario should output a reward of shape ().
Maybe it's a wrapper thing?
The text was updated successfully, but these errors were encountered: