Back to Search Start Over

Provably Efficient Model-Free Algorithms for Non-stationary CMDPs

Authors :
Wei, Honghao
Ghosh, Arnob
Shroff, Ness
Ying, Lei
Zhou, Xingyu
Source :
AISTATS 2023
Publication Year :
2023

Abstract

We study model-free reinforcement learning (RL) algorithms in episodic non-stationary constrained Markov Decision Processes (CMDPs), in which an agent aims to maximize the expected cumulative reward subject to a cumulative constraint on the expected utility (cost). In the non-stationary environment, reward, utility functions, and transition kernels can vary arbitrarily over time as long as the cumulative variations do not exceed certain variation budgets. We propose the first model-free, simulator-free RL algorithms with sublinear regret and zero constraint violation for non-stationary CMDPs in both tabular and linear function approximation settings with provable performance guarantees. Our results on regret bound and constraint violation for the tabular case match the corresponding best results for stationary CMDPs when the total budget is known. Additionally, we present a general framework for addressing the well-known challenges associated with analyzing non-stationary CMDPs, without requiring prior knowledge of the variation budget. We apply the approach for both tabular and linear approximation settings.

Details

Database :
arXiv
Journal :
AISTATS 2023
Publication Type :
Report
Accession number :
edsarx.2303.05733
Document Type :
Working Paper