DeepMind has open-sourced the heart of AlphaGo and AlphaZero

• leela-zero

  11 5,225 0.0 C++

  Go engine with no human-provided knowledge, modeled after the AlphaGo Zero paper.

  

Totally agree. I don't even know what benefit they'd get at this point from keeping some parts locked up.

Anyway if you want something runnable Leela has a nice reimplementation: https://github.com/leela-zero/leela-zero

• KataGo

  49 3,235 9.3 C++

  GTP engine and self-play learning in Go

I'd suggest KataGo, which is much stronger and more actively developed than Leela Zero https://github.com/lightvector/KataGo

• WorkOS

  workos.com sponsored

  The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.

  

• mctx

  10 2,203 0.0 Python

  Monte Carlo tree search in JAX

  

Interesting approach to private variables https://github.com/deepmind/mctx/blob/577fc77a3cda1b796e277e...

• alpha-zero-boosted

  2 79 3.2 Python

  A "build to learn" Alpha Zero implementation using Gradient Boosted Decision Trees (LightGBM)

> 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

Suggest a related project