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
i'm writing a custom environment and the action space for which is a tuple of a few different spaces. I was trying to use PPO, and i received the following error:
AssertionError: The algorithm only supports (<class 'gym.spaces.box.Box'>, <class 'gym.spaces.discrete.Discrete'>, <class 'gym.spaces.multi_discrete.MultiDiscrete'>, <class 'gym.spaces.multi_binary.MultiBinary'>) as action spaces but Tuple(Discrete(4), Box([0.], [1.], (1,), float32), Box([0. 0.], [1. 1.], (2,), float32), Box([-0.05 -0.05], [0.05 0.05], (2,), float32)) was provided
are there any algorithms that are ready for tuplized action spaces out the box? if not, do you have an idea for a workaround?
The text was updated successfully, but these errors were encountered:
i'm writing a custom environment and the action space for which is a tuple of a few different spaces. I was trying to use PPO, and i received the following error:
are there any algorithms that are ready for tuplized action spaces out the box? if not, do you have an idea for a workaround?
The text was updated successfully, but these errors were encountered: