mctx is a Monte Carlo Tree Search (MCTS) library developed by Google DeepMind for reinforcement learning research. It enables efficient and flexible implementation of MCTS algorithms, including those used in AlphaZero and MuZero.
Features
- Provides a general-purpose Monte Carlo Tree Search (MCTS) framework
- Supports AlphaZero, MuZero, and other learning-based MCTS variants
- Integrates with JAX for hardware-accelerated computations
- Designed for deep reinforcement learning and planning research
- Highly customizable search strategies and rollout policies
- Optimized for large-scale parallel computations
Categories
Reinforcement Learning AlgorithmsLicense
Apache License V2.0Follow Mctx
Other Useful Business Software
Gemini 3 and 200+ AI Models on One Platform
Build, govern, and optimize agents and models with Gemini Enterprise Agent Platform.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of Mctx!