Knowledge Graph

Graph explorer

Search resolved entities, walk their edges, and read the sentence behind every one.

Entities25 of 207,987

Entity

dual active reward learning

technology1 mentionslast seen Nov 10, 2026

Algorithm proposed for simultaneous selection of conversations and teachers to improve reward function learning from human feedback.

Relationships 2

dual active reward learningdepends onReinforcement Learning from Human Feedback88% confidence1 source
dual active reward learningapplies tolarge language model alignment80% confidence1 source

dual active reward learning

Relationship

dual active reward learningdepends onReinforcement Learning from Human Feedback

88% confidence1 supporting mentions

Either name opens that entity’s relationships.

Sources 1

preprintarXivNov 6, 2026Dual Active Learning for Reinforcement Learning from Human Feedback
we first propose a dual active reward learning algorithm for the simultaneous selection of conversations and teachers