Finite Time Analysis of Constrained Natural Critic-Actor Algorithm with Improved Sample Complexity

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Panda, Prashansa, Bhatnagar, Shalabh
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916990816354304
author Panda, Prashansa
Bhatnagar, Shalabh
author_facet Panda, Prashansa
Bhatnagar, Shalabh
contents Recent studies have increasingly focused on non-asymptotic convergence analyses for actor-critic (AC) algorithms. One such effort introduced a two-timescale critic-actor algorithm for the discounted cost setting using a tabular representation, where the usual roles of the actor and critic are reversed. However, only asymptotic convergence was established there. Subsequently, both asymptotic and non-asymptotic analyses of the critic-actor algorithm with linear function approximation were conducted. In our work, we introduce the first natural critic-actor algorithm with function approximation for the long-run average cost setting and under inequality constraints. We provide the non-asymptotic convergence guarantees for this algorithm. Our analysis establishes optimal learning rates and we also propose a modification to enhance sample complexity. We further show the results of experiments on three different Safety-Gym environments where our algorithm is found to be competitive in comparison with other well known algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2510_04189
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Finite Time Analysis of Constrained Natural Critic-Actor Algorithm with Improved Sample Complexity
Panda, Prashansa
Bhatnagar, Shalabh
Machine Learning
Artificial Intelligence
Recent studies have increasingly focused on non-asymptotic convergence analyses for actor-critic (AC) algorithms. One such effort introduced a two-timescale critic-actor algorithm for the discounted cost setting using a tabular representation, where the usual roles of the actor and critic are reversed. However, only asymptotic convergence was established there. Subsequently, both asymptotic and non-asymptotic analyses of the critic-actor algorithm with linear function approximation were conducted. In our work, we introduce the first natural critic-actor algorithm with function approximation for the long-run average cost setting and under inequality constraints. We provide the non-asymptotic convergence guarantees for this algorithm. Our analysis establishes optimal learning rates and we also propose a modification to enhance sample complexity. We further show the results of experiments on three different Safety-Gym environments where our algorithm is found to be competitive in comparison with other well known algorithms.
title Finite Time Analysis of Constrained Natural Critic-Actor Algorithm with Improved Sample Complexity
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2510.04189