A Sharper Global Convergence Analysis for Average Reward Reinforcement Learning via an Actor-Critic Approach

Swetha Ganesh; Washim Uddin Mondal; Vaneet Aggarwal

2025 ICML ICML 2025

A Sharper Global Convergence Analysis for Average Reward Reinforcement Learning via an Actor-Critic Approach

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.

Authors

Swetha Ganesh, Washim Uddin Mondal, Vaneet Aggarwal

Topics

Reinforcement Learning > Methods > Policy Learning

Keywords

markov decision processes convergence rate average reward state space monte carlo actor critic

Download PDF