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

Policy Gradient Penalty

technology1 mentionslast seen Sep 30, 2026

A single-loop policy-space method for constrained exploration in reinforcement learning that enforces occupancy-measure constraints via quadratic-penalty regularization.

Relationships 3

Policy Gradient Penalty

Relationship

Policy Gradient Penaltyapplies tocontinuous-control tasks

85% confidence1 supporting mentions

Either name opens that entity’s relationships.

Sources 1