Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling

Danil Provodin; Maurits Clemens Kaptein; Mykola Pechenizkiy

2024 ICML ICML 2024

Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Reinforcement Learning

Authors

Danil Provodin, Maurits Clemens Kaptein, Mykola Pechenizkiy

Topics

Machine Learning > Optimization & Theory > Bayesian Inference Reinforcement Learning > Applications > Robotics

Keywords

undiscounted setting posterior sampling regret bound cmdp near-optimal regret constrained markov decision processes

Download PDF