Hacker News Reader

s-cascion Show HN: Easily train AlphaZero-like agents on any environment you want

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

s-cascion Show HN: Easily train AlphaZero-like agents on any environment you want

Good catches, I've added the missing information. Thanks

s-cascion Show HN: Easily train AlphaZero-like agents on any environment you want

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!

s-cascion Show HN: Easily train AlphaZero-like agents on any environment you want

Interesting, I didn't know about it... Modifying the existing environments' interfaces shouldn't be too difficult. Feel free to submit a PR!

s-cascion Show HN: Easily train AlphaZero-like agents on any environment you want

There certainly are other projects around AlphaZero, I'd say this is simpler and much more basic

s-cascion Show HN: Easily train AlphaZero-like agents on any environment you want

If you do that, please submit a PR!