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

zeroth-order reward fine-tuning

technology1 mentionslast seen Sep 29, 2026

Anchor-guided optimization method that operates in trajectory space without policy likelihoods or reward gradients.

Relationships 1

zeroth-order reward fine-tuning

Relationship

DriveAnchordepends onzeroth-order reward fine-tuning

88% confidence1 supporting mentions

Either name opens that entity’s relationships.

Sources 1