Convergent Reinforcement Learning Algorithms for Stochastic Shortest Path Problem

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guin, Soumyajit, Bhatnagar, Shalabh
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908685855358976
author Guin, Soumyajit
Bhatnagar, Shalabh
author_facet Guin, Soumyajit
Bhatnagar, Shalabh
contents In this paper we propose two algorithms in the tabular setting and an algorithm for the function approximation setting for the Stochastic Shortest Path (SSP) problem. SSP problems form an important class of problems in Reinforcement Learning (RL), as other types of cost-criteria in RL can be formulated in the setting of SSP. We show asymptotic almost-sure convergence for all our algorithms. We observe superior performance of our tabular algorithms compared to other well-known convergent RL algorithms. We further observe reliable performance of our function approximation algorithm compared to other algorithms in the function approximation setting.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13963
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Convergent Reinforcement Learning Algorithms for Stochastic Shortest Path Problem
Guin, Soumyajit
Bhatnagar, Shalabh
Machine Learning
In this paper we propose two algorithms in the tabular setting and an algorithm for the function approximation setting for the Stochastic Shortest Path (SSP) problem. SSP problems form an important class of problems in Reinforcement Learning (RL), as other types of cost-criteria in RL can be formulated in the setting of SSP. We show asymptotic almost-sure convergence for all our algorithms. We observe superior performance of our tabular algorithms compared to other well-known convergent RL algorithms. We further observe reliable performance of our function approximation algorithm compared to other algorithms in the function approximation setting.
title Convergent Reinforcement Learning Algorithms for Stochastic Shortest Path Problem
topic Machine Learning
url https://arxiv.org/abs/2508.13963