https://github.com/lcswillems/torch-ac

Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPO
https://github.com/lcswillems/torch-ac

a2c a3c actor-critic advantage-actor-critic deep-reinforcement-learning minigrid multi-process ppo proximal-policy-optimization pytorch recurrent recurrent-neural-networks reinforcement-learning reward-shaping

Last synced: about 2 months ago
JSON representation

Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPO

• Host: GitHub
• URL: https://github.com/lcswillems/torch-ac
• Owner: lcswillems
• License: mit
• Created: 2019-04-07T08:47:24.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2022-10-05T23:17:23.000Z (almost 2 years ago)
• Last Synced: 2024-04-27T23:35:16.087Z (5 months ago)
• Topics: a2c, a3c, actor-critic, advantage-actor-critic, deep-reinforcement-learning, minigrid, multi-process, ppo, proximal-policy-optimization, pytorch, recurrent, recurrent-neural-networks, reinforcement-learning, reward-shaping
• Language: Python
• Homepage:
• Size: 23.4 KB
• Stars: 185
• Watchers: 8
• Forks: 64
• Open Issues: 6
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project