google-deepmind / mctxLinks
Monte Carlo tree search in JAX
☆2,587Updated 5 months ago
Alternatives and similar repositories for mctx
Users that are interested in mctx are comparing it to the libraries listed below
Sorting:
- Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.☆924Updated 2 years ago
- ♟️ Vectorized RL game environments in JAX☆583Updated 11 months ago
- Really Fast End-to-End Jax RL Implementations☆1,017Updated last year
- ☆1,403Updated last month
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,860Updated 7 months ago
- MuZero☆2,763Updated last year
- Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.☆1,407Updated 9 months ago
- ☆937Updated last year
- Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.☆866Updated last year
- JAX-based neural network library☆3,182Updated last week
- 🕹️ A diverse suite of scalable reinforcement learning environments in JAX☆802Updated 2 months ago
- ☆727Updated 2 years ago
- ☆2,812Updated last year
- Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.☆1,118Updated 2 weeks ago
- An algorithm that generalizes the paradigm of self-play reinforcement learning and search to imperfect-information games.☆689Updated last year
- Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary h…☆873Updated this week
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,299Updated last year
- RL Environments in JAX 🌍☆856Updated 8 months ago
- High throughput synchronous and asynchronous reinforcement learning☆972Updated last week
- Optax is a gradient processing and optimization library for JAX.☆2,174Updated this week
- Python-based research interface for blackbox and hyperparameter optimization, based on the internal Google Vizier Service.☆1,627Updated last week
- Massively parallel rigidbody physics simulation on accelerator hardware.☆3,048Updated this week
- A library of reinforcement learning components and agents☆3,914Updated this week
- Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/☆2,765Updated this week
- ☆924Updated last week
- ☆794Updated this week
- A platform for managing machine learning experiments☆895Updated this week
- The NetHack Learning Environment☆977Updated last year
- Grandmaster-Level Chess Without Search☆605Updated last year
- Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments☆1,136Updated 2 years ago