Policy Similarity Metric

Reinforcement LearningIntroduced 20002 papers
Source Paper

Description

Policy Similarity Metric, or PSM, is a similarity metric for measuring behavioral similarity between states in reinforcement learning. It assigns high similarity to states for which the optimal policies in those states as well as in future states are similar. PSM is reward-agnostic, making it more robust for generalization compared to approaches that rely on reward information.

Papers Using This Method

Label Ranker: Self-Aware Preference for Classification Label Position in Visual Masked Self-Supervised Pre-Trained Model2025-03-03Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning2021-01-13