ikostrikov/jaxrl
JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.
This project provides pre-built implementations of advanced reinforcement learning algorithms for continuous action spaces. Researchers and practitioners in fields like robotics, autonomous systems, or game AI can input their problem descriptions and desired reward structures to train intelligent agents. The output is a trained agent capable of making decisions in complex environments, which can then be used for simulations or real-world deployment.
753 stars. No commits in the last 6 months.
Use this if you are a machine learning researcher or engineer looking for clean, ready-to-use implementations of deep reinforcement learning algorithms in JAX to build upon for new research or to experiment with agent training.
Not ideal if you need reliable, production-ready baselines for benchmarking, as the project explicitly recommends using original implementations for such purposes.
Stars
753
Forks
74
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 26, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ikostrikov/jaxrl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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/