tera.ai

Knowledge Graph

Graph explorer

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

Entities25 of 207,987

All entities

Entity

doubly robust preference optimization

technology1 mentionslast seen Oct 28, 2026

An algorithm proposed to address model misspecification in RLHF, remaining consistent when either the preference model or reference policy is correctly specified.

Relationships 2

doubly robust preference optimization

Relationship

doubly robust preference optimizationdepends onReinforcement Learning from Human Feedback

85% confidence1 supporting mentions

Either name opens that entity’s relationships.

Sources 1