Only One Player: Can we use MuZero?

werner-duvaud / muzero-general

MuZero

https://github.com/werner-duvaud/muzero-general/wiki/MuZero-Documentation

MIT License

2.42k stars 602 forks source link

Only One Player: Can we use MuZero? #210

Open 1121091694 opened 1 year ago

1121091694 commented 1 year ago

Search before asking

[X] I have searched the MuZero issues and found no similar feature requests.

Description

Perfect ideas and codes In my game, there is only one player, constantly moving, assessing the situation, and there is a final reward. How can I use Muzero to optimize AI games? Is there a tutorial for single player training and use?

Additional context

No response

AdrianAcala commented 1 year ago

Check out the twenty-one game. It is only one player.

https://github.com/werner-duvaud/muzero-general/blob/master/games/twentyone.py

puyuan1996 commented 3 months ago

Hello, thank you to the contributors for their outstanding work on this repository. Regarding the issue you've raised, you might be interested in the project "LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios". This repository not only supports the AlphaZero algorithm but also extends support to MuZero and a series of related algorithms and environments, which might meet your requirements. Best wishes.