Brad Knox

wbknox's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 3 papers about 2 years ago

Contrastive Prefence Learning: Learning from Human Feedback without RL

Paper • 2310.13639 • Published Oct 20, 2023 • 25

Learning Optimal Advantage from Preferences and Mistaking it for Reward

Paper • 2310.02456 • Published Oct 3, 2023 • 1

Models of human preference for learning reward functions

Paper • 2206.02231 • Published Jun 5, 2022