PrototypeCommon
nakamotoo/Cal-QL
official implementation for our paper Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning (NeurIPS 2023)
- Owner
- nakamotoo (personal account)
- Stars
- Stars: 124
- Forks
- Forks: 8
- Language
- Python
- License
- None
- Created
- 2023
- Topics
- offline-rloffline-to-online-rlreinforcement-learning
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by nakamotoo
All 2 repos by nakamotoo- nakamotoo/dsrl_pi0Stars: 307PythonAlpha
Nearby in Python
All Python repos- TttMc/mcd-budget-biteStars: 124PythonPrototype
- ant-intl/BizAgentBenchStars: 124PythonPrototype
- Wholiver/metis-reverseStars: 124PythonPrototype
- labjack/LabJackPythonStars: 124PythonPrototype
- django-cms/cmsplugin-filerStars: 124PythonPrototype
- OpenTreeMap/otm-legacyStars: 124PythonPrototype