Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation

Yudan Wang; Yue Wang; Yi Zhou; Shaofeng Zou

2024 ICML ICML 2024

Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation

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

Yudan Wang, Yue Wang, Yi Zhou, Shaofeng Zou

Topics

Reinforcement Learning > Methods > Policy Learning

Keywords

natural actor-critic actor critic single loop compatible function approximation markovian sample trajectory non-asymptotic convergence bounds

Download PDF