https://github.com/tinkoff-ai/CORL

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC
https://github.com/tinkoff-ai/CORL

d4rl gym offline-reinforcement-learning reinforcement-learning

Last synced: about 2 months ago
JSON representation

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

• Host: GitHub
• URL: https://github.com/tinkoff-ai/CORL
• Owner: tinkoff-ai
• License: apache-2.0
• Archived: true
• Created: 2022-09-23T08:43:54.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2023-08-03T07:13:55.000Z (about 1 year ago)
• Last Synced: 2024-05-21T12:42:45.445Z (4 months ago)
• Topics: d4rl, gym, offline-reinforcement-learning, reinforcement-learning
• Language: Python
• Homepage: https://arxiv.org/abs/2210.07105
• Size: 3.33 MB
• Stars: 981
• Watchers: 15
• Forks: 112
• Open Issues: 4
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE
  • Codeowners: .github/CODEOWNERS

Awesome Lists containing this project