RCEpic
ikostrikov/pytorch-a2c-ppo-acktr-gail
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
- Owner
- ikostrikov (personal account)
- Stars
- Stars: 3,909
- Forks
- Forks: 840
- Language
- Python
- License
- MIT
- Created
- 2017
- Topics
- pytorchreinforcement-learningdeep-learningdeep-reinforcement-learningactor-criticadvantage-actor-critica2cppoproximal-policy-optimizationacktr
- Tier
- RC (2,000 to 4,999 ★) What this tier means
More repos by ikostrikov
All 12 repos by ikostrikov- ikostrikov/pytorch-a3cStars: 1,338PythonBeta
- ikostrikov/jaxrlStars: 759Jupyter NotebookBeta
- ikostrikov/TensorFlow-VAE-GAN-DRAWStars: 592PythonAlpha
- ikostrikov/pytorch-flowsStars: 589PythonAlpha
- ikostrikov/pytorch-trpoStars: 450PythonAlpha
- ikostrikov/rlpdStars: 420PythonAlpha
Nearby in Python
All Python repos- hustvl/VimStars: 3,914PythonRC
- open-mmlab/mmtrackingStars: 3,912PythonRC
- Sentdex/pygta5Stars: 3,910PythonRC
- pyload/pyloadStars: 3,905PythonRC
- spaceandtimefdn/SxT-Python-SDKStars: 3,905PythonRC
- pipeshub-ai/pipeshub-aiStars: 3,905PythonRC