Enhancing Policy Gradient with the Polyak Step-Size Adaption

Bibliographic Details
Title: Enhancing Policy Gradient with the Polyak Step-Size Adaption
Authors: Li, Yunxiang, Yuan, Rui, Fan, Chen, Schmidt, Mark, Horváth, Samuel, Gower, Robert M., Takáč, Martin
Publication Year: 2024
Collection: Computer Science
Subject Terms: Computer Science - Machine Learning
More Details: Policy gradient is a widely utilized and foundational algorithm in the field of reinforcement learning (RL). Renowned for its convergence guarantees and stability compared to other RL algorithms, its practical application is often hindered by sensitivity to hyper-parameters, particularly the step-size. In this paper, we introduce the integration of the Polyak step-size in RL, which automatically adjusts the step-size without prior knowledge. To adapt this method to RL settings, we address several issues, including unknown f* in the Polyak step-size. Additionally, we showcase the performance of the Polyak step-size in RL through experiments, demonstrating faster convergence and the attainment of more stable policies.
Document Type: Working Paper
Access URL: http://arxiv.org/abs/2404.07525
Accession Number: edsarx.2404.07525
Database: arXiv
More Details
Description not available.