The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
Describe the bug
in the the _update_action_spaces method of the UnityPettingzooBaseEnv class, you force the actions to be of int32 and in the [-1,1] range (see the code below). This constraint doesn't apply to all scenarios
Describe the bug in the the
_update_action_spaces
method of the UnityPettingzooBaseEnv class, you force the actions to be of int32 and in the [-1,1] range (see the code below). This constraint doesn't apply to all scenariosIt makes more sense to use the same logic as in
_update_observation_spaces
.I'm aware that this issue was raised previously, but it is still present.
Console logs / stack traces The action to send is
But I get this
Environment :