Multi-State TD Target for Model-Free Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Wuhao, Chen, Zhiyong, Zhang, Lepeng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911975021215744
author Wang, Wuhao
Chen, Zhiyong
Zhang, Lepeng
author_facet Wang, Wuhao
Chen, Zhiyong
Zhang, Lepeng
contents Temporal difference (TD) learning is a fundamental technique in reinforcement learning that updates value estimates for states or state-action pairs using a TD target. This target represents an improved estimate of the true value by incorporating both immediate rewards and the estimated value of subsequent states. Traditionally, TD learning relies on the value of a single subsequent state. We propose an enhanced multi-state TD (MSTD) target that utilizes the estimated values of multiple subsequent states. Building on this new MSTD concept, we develop complete actor-critic algorithms that include management of replay buffers in two modes, and integrate with deep deterministic policy optimization (DDPG) and soft actor-critic (SAC). Experimental results demonstrate that algorithms employing the MSTD target significantly improve learning performance compared to traditional methods.The code is provided on GitHub.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16522
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-State TD Target for Model-Free Reinforcement Learning
Wang, Wuhao
Chen, Zhiyong
Zhang, Lepeng
Machine Learning
Artificial Intelligence
68T05(Primary)
Temporal difference (TD) learning is a fundamental technique in reinforcement learning that updates value estimates for states or state-action pairs using a TD target. This target represents an improved estimate of the true value by incorporating both immediate rewards and the estimated value of subsequent states. Traditionally, TD learning relies on the value of a single subsequent state. We propose an enhanced multi-state TD (MSTD) target that utilizes the estimated values of multiple subsequent states. Building on this new MSTD concept, we develop complete actor-critic algorithms that include management of replay buffers in two modes, and integrate with deep deterministic policy optimization (DDPG) and soft actor-critic (SAC). Experimental results demonstrate that algorithms employing the MSTD target significantly improve learning performance compared to traditional methods.The code is provided on GitHub.
title Multi-State TD Target for Model-Free Reinforcement Learning
topic Machine Learning
Artificial Intelligence
68T05(Primary)
url https://arxiv.org/abs/2405.16522