policy gradient

Definition

A reinforcement-learning method that nudges a model's behavior toward actions that scored higher.

A family of RL algorithms that estimate gradients of expected return with respect to policy parameters by sampling trajectories.

Also called: policy-gradient

Mentioned in 5 episodes

1. 079
   An Old Idea From Cognitive Psychology Reshapes How We Reward Reasoning Models
2. 060
   When Splitting One Model Across Three Agents Doubles Its Accuracy
3. 028
   Teaching a Model to Hire Copies of Itself: Recursive Agent Optimization
4. 025
   The Missing Gradient Term That Predicts Sycophancy in RLHF
5. 010
   When Reward Climbs But Reasoning Goes Generic: Diagnosing Template Collapse in Agentic RL

Related concepts