https://github.com/jeremy-collins/robot-rlhf

Robot Learning from Human Feedback. Inspired by advancements in NLP, we train a robot policy via reinforcement learning using a reward function learned exclusively from human preferences.
https://github.com/jeremy-collins/robot-rlhf

alignment chatgpt reinforcement-learning rlhf robotics

Last synced: 4 months ago
JSON representation

Robot Learning from Human Feedback. Inspired by advancements in NLP, we train a robot policy via reinforcement learning using a reward function learned exclusively from human preferences.

• Host: GitHub
• URL: https://github.com/jeremy-collins/robot-rlhf
• Owner: jeremy-collins
• Created: 2023-04-16T02:39:45.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2023-04-16T02:42:49.000Z (about 1 year ago)
• Last Synced: 2024-01-16T13:14:33.395Z (6 months ago)
• Topics: alignment, chatgpt, reinforcement-learning, rlhf, robotics
• Language: Python
• Homepage:
• Size: 348 KB
• Stars: 2
• Watchers: 2
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Lists

• awesome-human-in-the-loop - Github - jeremy-collins/robot-rlhf

README

        
# robot-rlhf

Robot Learning through Human Feedback. Inspired by advancements in NLP, we train a robot policy via reinforcement learning using a reward function learned exclusively from human preferences.