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

[IEEE ToG] MiniZero: An AlphaZero and MuZero Training Framework

High-throughput, sub-millisecond Reinforcement Learning engine. Built in Rust and CUDA with a Python/LangGraph orchestration layer. Implements Gumbel MuZero MCTS and lock-free concurrency, entirely bypassing the Python GIL to achieve massive evaluation scale without GPU thread divergence.