jaxrl
by ikostrikov · GitHub
JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.
# batch-reinforcement-learning# behavioral-cloning# continuous-control# deep-deterministic-policy-gradient
⭐ Stars
757
🍴 Forks
75
📜 License
MIT
Commercial use OK📅 Created
2021
🔄 Last commit
3 yr ago
🏷️ Category
batch-reinforcement-learning
💻 Language
You maintain this project?
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
📈 Star history
2026-07-202026-07-21
📄 About
JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.
❓ Frequently asked questions
What is jaxrl?
JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.
Is jaxrl open source?
jaxrl is an open-source project. It is released under the MIT license.
Is jaxrl free?
Yes. jaxrl is free and open source — you can use, modify and self-host it.
🏅 Maintainer of this project?
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://opensourceai.tech/project/ikostrikov-jaxrl.html)
🧬 Related projects🧬 View the DNA map →
My_Bibliography_for_Research_on_Autonomous_Driving
Personal notes about scientific and research works on "Decision-Making for Autonomous Driving"
★ 470 · behavioral-cloning
kanachan
A Japanese (Riichi) Mahjong AI Framework
★ 342 · behavioral-cloning
rl-tools
The Fastest Deep Reinforcement Learning Library
★ 1k · continuous-control