Our great sponsors
-
WorkOS
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.
-
alpha-zero-boosted
A "build to learn" Alpha Zero implementation using Gradient Boosted Decision Trees (LightGBM)
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
I'd suggest KataGo, which is much stronger and more actively developed than Leela Zero https://github.com/lightvector/KataGo
Interesting approach to private variables https://github.com/deepmind/mctx/blob/577fc77a3cda1b796e277e...
> 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
Related posts
- MuZero: Mastering Go, chess, shogi and Atari without rules
- LLeaves: A LLVM-based compiler for LightGBM decision trees
- Machine learning & operations research
- Tree compiler that speeds up LightGBM model inference by ~30x
- Is it possible to clean memory after using a package that has a memory leak in my python script?