s-casci
Joined 2 years ago
Karma
43
Submissions
9
Member since
Dec 20
Recent submissions
Comment · 2 years ago
The policy function outputs the probability of taking every possible (legal or illegal) action. Once you have a way of indexing those actions, both the policy and the game need to refer to the same thing when indexing the same number
Comment · 2 years ago
Good catches, I've added the missing information. Thanks
Comment · 2 years ago
AlphaZero has been made for perfect information games. That said, the Monte Carlo Tree Search in the library can be run with any agent that implements a value and policy function. So, while the AlphaZeroAgent in agents.py wouldn't fit the problem you are describing, implementing something like Meta's ReBeL (https://ai.meta.com/blog/rebel-a-general-game-playing-ai-bot...) shouldn't be an impossible task. The Monte Carlo Tree Search algorithm in mcts.py has been written to be modular from the start exactly to do something like this!
Comment · 2 years ago
Interesting, I didn't know about it... Modifying the existing environments' interfaces shouldn't be too difficult. Feel free to submit a PR!
Comment · 2 years ago
There certainly are other projects around AlphaZero, I'd say this is simpler and much more basic
Comment · 2 years ago
If you do that, please submit a PR!