MichaelTMatthews/Craftax
(Crafter + NetHack) in JAX. ICML 2024 Spotlight.
Craftax provides a robust reinforcement learning environment designed for training and evaluating AI agents in complex, goal-oriented tasks. It simulates a game world inspired by Minecraft-style crafting and roguelike exploration, where agents must gather resources, craft items, build structures, and interact with the environment to achieve objectives. This tool is intended for AI researchers and practitioners focused on developing and testing advanced reinforcement learning algorithms.
378 stars. Available on PyPI.
Use this if you need a challenging and extensible simulation environment to develop, benchmark, and compare reinforcement learning agents, especially for tasks requiring long-term planning, exploration, and resource management.
Not ideal if you are looking for a simple, pre-built game for entertainment, as this is primarily an infrastructure for AI experimentation.
Stars
378
Forks
44
Language
Python
License
MIT
Category
Last pushed
Feb 10, 2026
Commits (30d)
0
Dependencies
8
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MichaelTMatthews/Craftax"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
explosion/thinc
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
google-deepmind/optax
Optax is a gradient processing and optimization library for JAX.
patrick-kidger/diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable....
google/grain
Library for reading and processing ML training data.
patrick-kidger/equinox
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/