Get a policy-gradient agent to train on MazeBase

[hsclouse]

• Want a single policy-gradient agent (in PyTorch) to train on the SingleGoal game.
• started over with the policy gradient agent myself instead of trying to aggregate existing code.
  • had originally tried to use policy-gradient code and incorporate MazeBase.
  • now, trying to build policy-gradient from the ground up around MazeBase.
  • Need to make the rewards match.

[hsclouse]

Code is here

[tesatory]

Is it still not working? do you want me to take a look?

[hsclouse]

Not right now. Thanks, though. I just wanted to add you for future reference. :)

…

On Mon, Apr 24, 2017 at 8:22 PM, Sainbayar Sukhbaatar < ***@***.***> wrote: Is it still not working? do you want me to take a look? — You are receiving this because you were assigned. Reply to this email directly, view it on GitHub <#1 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AGeKNnz9kl0TBduZLbyQhBJ9StVrLr6Lks5rzTy2gaJpZM4NGuHm> .