Finite-Time Analysis of Three-Timescale Constrained Actor-Critic and Constrained Natural Actor-Critic Algorithms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Panda, Prashansa, Bhatnagar, Shalabh
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915468901613568
author Panda, Prashansa
Bhatnagar, Shalabh
author_facet Panda, Prashansa
Bhatnagar, Shalabh
contents Actor Critic methods have found immense applications on a wide range of Reinforcement Learning tasks especially when the state-action space is large. In this paper, we consider actor critic and natural actor critic algorithms with function approximation for constrained Markov decision processes (C-MDP) involving inequality constraints and carry out a non-asymptotic analysis for both of these algorithms in a non-i.i.d (Markovian) setting. We consider the long-run average cost criterion where both the objective and the constraint functions are suitable policy-dependent long-run averages of certain prescribed cost functions. We handle the inequality constraints using the Lagrange multiplier method. We prove that these algorithms are guaranteed to find a first-order stationary point (i.e., $\Vert \nabla L(θ,γ)\Vert_2^2 \leq ε$) of the performance (Lagrange) function $L(θ,γ)$, with a sample complexity of $\mathcal{\tilde{O}}(ε^{-2.5})$ in the case of both Constrained Actor Critic (C-AC) and Constrained Natural Actor Critic (C-NAC) algorithms. We also show the results of experiments on three different Safety-Gym environments.
format Preprint
id arxiv_https___arxiv_org_abs_2310_16363
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Finite-Time Analysis of Three-Timescale Constrained Actor-Critic and Constrained Natural Actor-Critic Algorithms
Panda, Prashansa
Bhatnagar, Shalabh
Machine Learning
Actor Critic methods have found immense applications on a wide range of Reinforcement Learning tasks especially when the state-action space is large. In this paper, we consider actor critic and natural actor critic algorithms with function approximation for constrained Markov decision processes (C-MDP) involving inequality constraints and carry out a non-asymptotic analysis for both of these algorithms in a non-i.i.d (Markovian) setting. We consider the long-run average cost criterion where both the objective and the constraint functions are suitable policy-dependent long-run averages of certain prescribed cost functions. We handle the inequality constraints using the Lagrange multiplier method. We prove that these algorithms are guaranteed to find a first-order stationary point (i.e., $\Vert \nabla L(θ,γ)\Vert_2^2 \leq ε$) of the performance (Lagrange) function $L(θ,γ)$, with a sample complexity of $\mathcal{\tilde{O}}(ε^{-2.5})$ in the case of both Constrained Actor Critic (C-AC) and Constrained Natural Actor Critic (C-NAC) algorithms. We also show the results of experiments on three different Safety-Gym environments.
title Finite-Time Analysis of Three-Timescale Constrained Actor-Critic and Constrained Natural Actor-Critic Algorithms
topic Machine Learning
url https://arxiv.org/abs/2310.16363