hanjuku-kaso/awesome-offline-rl
An indexed collection of algorithms and research papers for offline reinforcement learning.
★1.1k stars Learning
Not currently ranked — collecting fresh signals.
star history
This repository curates academic papers and algorithms for offline reinforcement learning, organized into sections covering surveys, theoretical methods, benchmarks, applications, and off-policy evaluation techniques. Maintained by researchers at Cornell University and Hanjuku-kaso Co., Ltd.
Frequently asked
- What is hanjuku-kaso/awesome-offline-rl?
- An indexed collection of algorithms and research papers for offline reinforcement learning.
- Is awesome-offline-rl open source?
- Yes — hanjuku-kaso/awesome-offline-rl is an open-source project tracked on heatdrop.
- How popular is awesome-offline-rl?
- hanjuku-kaso/awesome-offline-rl has 1.1k stars on GitHub.
- Where can I find awesome-offline-rl?
- hanjuku-kaso/awesome-offline-rl is on GitHub at https://github.com/hanjuku-kaso/awesome-offline-rl.