https://github.com/Cornell-RL/drpo

Dateset Reset Policy Optimization
https://github.com/Cornell-RL/drpo

Last synced: 5 months ago
JSON representation

Dateset Reset Policy Optimization

• Host: GitHub
• URL: https://github.com/Cornell-RL/drpo
• Owner: Cornell-RL
• License: apache-2.0
• Created: 2024-04-12T13:43:03.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-04-12T13:53:22.000Z (about 1 year ago)
• Last Synced: 2024-09-03T03:01:55.672Z (8 months ago)
• Language: Python
• Size: 32.2 KB
• Stars: 25
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-RLHF - official

README

        
# Dateset Reset Policy Optimization (DR-PO)

Fork of [Learning from Feedback Details](https://github.com/vwxyzjn/summarize_from_feedback_details/tree/62c37d63c212c55bde52833611eb642a95facb5c) for DR-PO and TL;DR.

More information coming soon...