StableVery rare
vwxyzjn/cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
- Owner
- vwxyzjn (personal account)
- Stars
- Stars: 10,634
- Forks
- Forks: 1,195
- Language
- Python
- License
- None
- Created
- 2019
- Topics
- wandbreinforcement-learningpytorchpythongymmachine-learningdeep-reinforcement-learningdeep-learningatariale
- Tier
- Stable (5,000 to 19,999 ★) What this tier means
More repos by vwxyzjn
All 7 repos by vwxyzjn- vwxyzjn/ppo-implementation-detailsStars: 963PythonBeta
- vwxyzjn/portwardenStars: 637GoAlpha
- vwxyzjn/lm-human-preference-detailsStars: 200PythonPrototype
- vwxyzjn/invalid-action-maskingStars: 171PythonPrototype
- vwxyzjn/summarize_from_feedback_detailsStars: 165PythonPrototype
- vwxyzjn/cleanbaStars: 127PythonPrototype
Nearby in Python
All Python repos- ollama/ollama-pythonStars: 10,666PythonStable
- taojy123/KeymouseGoStars: 10,651PythonStable
- paralax/awesome-honeypotsStars: 10,647PythonStable
- ultralytics/yolov3Stars: 10,633PythonStable
- facebookresearch/ParlAIStars: 10,616PythonStable
- prompt-toolkit/python-prompt-toolkitStars: 10,608PythonStable