method · first seen 17 Oct 2026
reward learning from preferences
Also: preference-based reward learning
Learning a reward function from human preference comparisons to guide policy optimization.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Steerable Pluralistic Policy Alignment from Anonymized Crowd FeedbackPapers · 17 Oct 2026 · Akansha Kalra, Ellen R. Novoseller, Vernon J. Lawhern, Daniel S. Brown
Latest sources
- Steerable Pluralistic Policy Alignment from Anonymized Crowd FeedbackPapers · 17 Oct 2026 · Akansha Kalra, Ellen R. Novoseller, Vernon J. Lawhern, Daniel S. Brown