Skip to content
conftrace_
2025 ICML ICML 2025

Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity

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 - Mathematics & Optimization and Reinforcement Learning

Authors

Qiuhao Wang, Yuqi Zha, Chin Pang Ho, Marek Petrik

Topics

Reinforcement Learning > Methods > Policy Learning Mathematics & Optimization > Optimization > Continuous Optimization Mathematics & Optimization > Optimization > Stochastic Methods

Keywords

policy gradient convergence analysis projected policy gradient adaptive tolerance robust average-reward mdps transition evaluation
Download PDF