search

AppliedDataSciencePartners / DeepReinforcementLearning

A replica of the AlphaZero methodology for deep reinforcement learning in Python
GNU General Public License v3.0
2.02k stars 758 forks source link

Interested in implementing other games #49

Open HamzaEzzRa opened 4 years ago

HamzaEzzRa commented 4 years ago

I was going through the code and thinking of the changes that should be made in the case of a more complex game (Chess for example...) where ideally the allowed actions would be a list of tuples (piece position, target position), and I'm having a slight suspicion that the agent code has to be altered in some way. Any input on this ?

luiskarlos commented 3 years ago

I am also interested in experimenting with new games, my first step is to refactor the code, you can see my progress here any feedback will be appreciated.

archcra commented 3 years ago

I have already done this in two games: https://github.com/archcra/wu-hu-qi https://github.com/archcra/tic-tac-toe-az

Hope those help.

luiskarlos commented 3 years ago

I have already done this in two games: https://github.com/archcra/wu-hu-qi https://github.com/archcra/tic-tac-toe-az

Hope those help.

thanks, it will help 👍

ItamarDouek commented 2 years ago

i am also trying to get this code working for chess, did it work for you?

luiskarlos commented 2 years ago

No the code is a good start, but it needs a lot of refine