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
Great project, thanks for sharing. It would be great to have more flexibility between the agent and the environment. For instance, many environments mask out the actions by setting them to int.MinValue.
Would it be possible to return the array of all actions before the argmax? Then add a method for the iEnvironment, something like MaskActions(actionIds)?
The text was updated successfully, but these errors were encountered:
Great project, thanks for sharing. It would be great to have more flexibility between the agent and the environment. For instance, many environments mask out the actions by setting them to int.MinValue.
Would it be possible to return the array of all actions before the
argmax
? Then add a method for the iEnvironment, something like MaskActions(actionIds)?The text was updated successfully, but these errors were encountered: