Alphazero Python Packages

pgx

♟️ Vectorized RL game environments in JAX

lightzero

[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)

trimcts

High-performance C++ implementation of Monte Carlo Tree Search (MCTS) with Python bindings. Supports AlphaZero and MuZero paradigms, featuring batched network evaluation and efficient tree reuse.

reinfors

High-throughput reinforcement-learning search and sampling in Rust, with caller-owned Python networks and training

alphatriangle

An AlphaZero-style AI agent for a custom triangle puzzle game. Features distributed self-play with Ray, a C++ MCTS core, and a PyTorch neural network. Includes async logging via MLflow & TensorBoard.

zero-play

Teach a computer to play any game.

dopamax

Reinforcement learning in pure JAX.

lczero-bindings

Open source neural network chess engine with GPU acceleration and broad hardware support.

hometrainer

generic python implementation of the alpha zero algorithm