I'm trying to make an AI to play my own card game.

I have an OpenAI gym for the game with Dict as an observation space. It is nested dict, so I can't easily replace it with a tuple. I want to pass this observation space as model input.

Do I need to encode this observation space in some multidimensional array by myself? I thought there should be some code in gym/keras-rl that would help me with that task.

  • $\begingroup$ I found flatten function in gym repo, it looks like is the thing what I'm looking for. $\endgroup$ – rnd_d Jun 8 '19 at 19:48
  • $\begingroup$ Can you explain more about this? I am having the same problem. I'm having several MultiDiscrete inputs and I don't know how to feed them into the training algorithm without using Dict. $\endgroup$ – Saeid Ghafouri Apr 7 at 20:17

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.