Rating-Correlations
alpha-zero-boosted
Rating-Correlations | alpha-zero-boosted | |
---|---|---|
3 | 2 | |
1 | 79 | |
- | - | |
3.3 | 3.2 | |
about 1 year ago | almost 4 years ago | |
Python | Python | |
Apache License 2.0 | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Rating-Correlations
-
Contribute to chessprogramming.org
maybe ask ferdy from chess stackexchange aka fsmosca from github aka Ferdinand Mosca who has a chessprogramming.org page here?
-
the lichess rating correlation web app is done! (ratingcorrelations.herokuapp.com) unlike chessratingcomparison.com, it allows multiple inputs and has outputs for chess960 and crazyhouse!
shared on github! https://github.com/fsmosca/Rating-Correlations/issues/3
This appears to have been created by a github user named fsmosca aka Philippine mechanical engineer Ferdinand Mosca. See here for rating correlations.
alpha-zero-boosted
-
DeepMind has open-sourced the heart of AlphaGo and AlphaZero
> I came up with a nifty implementation in Python that outperforms the naive impl by 30x, allowing a pure python MCTS/NN interop implementation. See https://www.moderndescartes.com/essays/deep_dive_mcts/
Great post!
Chasing pointers in the MCTS tree is definitely a slow approach. Although typically there are < 900 "considerations" per move for alphazero. I've found getting value/policy predictions from a neural network (or GBDT[1]) for the node expansions during those considerations is at least an order of magnitude slower than the MCTS tree-hopping logic.
[1] https://github.com/cgreer/alpha-zero-boosted
-
MuZero: Mastering Go, chess, shogi and Atari without rules
What you can do is checkout the algorithm at a particular stages of development. AlphaZero&Friends start out not being very good at the game, then over time they learn and become super human. You typically checkpoint the weights for the model at various stages. So early on, the algo would be like a 600 elo player for chess and then eventually get to superhuman elo levels. So if you wanted to train you can gradually play against versions of the algo until you can beat them by loading up the weights at various difficulty stages.
I implemented AlphaZero (but not Mu yet) using GBDTs instead of NNs here if you're curious about how it would work: https://github.com/cgreer/alpha-zero-boosted. Instead of saving the "weights" for a GBDT, you save the splitpoints for the value/policy models, but the concept is the same.
What are some alternatives?
AutoViz - Automatically Visualize any dataset, any size with a single line of code. Created by Ram Seshadri. Collaborators Welcome. Permission Granted upon Request.
KataGo - GTP engine and self-play learning in Go
m2cgen - Transform ML models into a native code (Java, C, Python, Go, JavaScript, Visual Basic, C#, R, PowerShell, PHP, Dart, Haskell, Ruby, F#, Rust) with zero dependencies
neural_network_chess - Free Book about Deep-Learning approaches for Chess (like AlphaZero, Leela Chess Zero and Stockfish NNUE)
Hyperactive - An optimization and data collection toolbox for convenient and fast prototyping of computationally expensive models.
katrain - Improve your Baduk skills by training with KataGo!