-
hi,
i was wondering if i can apply the baselines algo on the game chess either https://github.com/genyrosk/gym-chess or a custom chess env. based on python-chess.
i was thinking 18x8x8 input and 6…
-
The idea was said by Jonathan:
"I guess what you've have to do is generate many samples of the kind that are stored in AlphaZero's memory buffer. You can take these samples either from human play dat…
-
在敲你的代码过程中遇到了两个问题,麻烦您给指导一下:
1. 根据AlphaGo Zero论文中的描述,在MCTS的backup过程中,首先根据policy-value network得到叶子节点的p,v,之后使用v来更新各个树内节点的Q值。在你的代码中使用的是函数update_recursive(leaf_value),这其中的leaf_value应该就是论文中该叶子节点的v对吧?为什么在mct…
-
### Search before asking
- [X] I have searched the MuZero [issues](https://github.com/werner-duvaud/muzero-general/issues) and found no similar feature requests.
### Description
Hey,
I'm wonder…
-
FYI: https://arxiv.org/abs/1712.01815
-
What is the purpose of this project?
What is it meant to achieve?
What will be the deliverables?
-
### Search before asking
- [X] I have searched the MuZero [issues](https://github.com/werner-duvaud/muzero-general/issues) and found no similar feature requests.
### Description
Is there a success…
-
We need some kind of AI to play with and evaluate our agent after training. There are many algorithms we can implement and in this project, we can try the **MiniMax** algorithm with and without _alpha…
-
I started researching the alpha-zero-general algorithm, but I found this parameter in the main.py module
> 'updateThreshold': 0.6, # During arena playoff, new neural net will be accepted if threshold…
-
### Search before asking
- [X] I have searched the MuZero [issues](https://github.com/werner-duvaud/muzero-general/issues) and found no similar feature requests.
### Description
Perfect ideas and…