https://github.com/luchris429/purejaxrl

Really Fast End-to-End Jax RL Implementations
https://github.com/luchris429/purejaxrl

deep-reinforcement-learning jax ppo reinforcement-learning reinforcement-learning-algorithms

Last synced: 12 days ago
JSON representation

Really Fast End-to-End Jax RL Implementations

• Host: GitHub
• URL: https://github.com/luchris429/purejaxrl
• Owner: luchris429
• License: apache-2.0
• Created: 2023-02-25T15:38:11.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-08-16T15:28:16.000Z (3 months ago)
• Last Synced: 2024-08-16T17:01:46.047Z (3 months ago)
• Topics: deep-reinforcement-learning, jax, ppo, reinforcement-learning, reinforcement-learning-algorithms
• Language: Python
• Homepage:
• Size: 1.69 MB
• Stars: 655
• Watchers: 11
• Forks: 54
• Open Issues: 11
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-jax - purejaxrl - Vectorisable, end-to-end RL algorithms in JAX. <img src="https://img.shields.io/github/stars/luchris429/purejaxrl?style=social" align="center"> (Libraries / New Libraries)