How Do Offline Measures For Exploration In Reinforcement Learning Behave?

Abstract

Sufficient exploration is paramount for the success of a reinforcement learning agent. Yet, exploration is rarely assessed in an algorithm-independent way. We compare the behavior of three data-based, offline exploration metrics described in the literature on intuitive simple distributions and highlight problems to be aware of when using them. We propose a fourth metric,uniform relative entropy, and implement it using either a k-nearest-neighbor or a nearest-neighbor-ratio estimator, highlighting that the implementation choices have a profound impact on these measures.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhollenstein2020how

Related papers

• A Dataset Perspective On Offline Reinforcement Learning (2021)0.00
• Behavioral Entropy-guided Dataset Generation For Offline Reinforcement Learning (2025)0.00
• Maximum Entropy Exploration Without The Rollouts (2026)0.00
• Don't Change The Algorithm, Change The Data: Exploratory Data For Offline Reinforcement Learning (2022)0.00
• Offline Meta Learning Of Exploration (2020)0.00
• Exploration By Random Distribution Distillation (2025)0.00
• Revisiting Design Choices In Offline Model-based Reinforcement Learning (2021)6.34
• Measuring Data Quality For Dataset Selection In Offline Reinforcement Learning (2021)0.00