How to build a comunication interface between a reinforcement learning and a videogame?

Question

I want to try to build a reinforcement learning model in order to play old arcade videogame, I know about projects in order to build AI for playing videogames, but I don't know how could I build an interface between a videogame and a python app in order to train the model while the model is playing.

is there any library in order to train a reinforcement learning model using an emulator or something like that on python? How can I build an app like that?

Thanks

Answer 1

You might wanna check OPEN AI GYM The project has several environments for atari games, robotics and a lot of other useful resources on reinforcement learning. I think this good place to start. If you need a bridge for some specific game, you need to google, for example there is repo for TorchCraft - A bridge between Torch and StarCraft.