A family of \(s\)-rectangular robust MDPs: relative conservativeness, asymptotic analyses, and finite-sample properties

DOI10.1137/23M1559920MaRDI QIDQ6495779

Archis Ghate, Sivaramakrishnan Ramani

Publication date: 2 May 2024

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

zbMATH Keywords

dynamic programmingdistributionally robust optimizationsample complexityvalue convergenceprobabilistic performance guarantees

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40) Robustness in mathematical programming (90C17)

Cites Work

• Unnamed Item
• Unnamed Item
• Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
• Toward theoretical understandings of robust Markov decision processes: sample complexity and asymptotics
• Robust MDPs with k-Rectangular Uncertainty
• Percentile Optimization for Markov Decision Processes with Parameter Uncertainty
• The Concise Encyclopedia of Statistics
• Markovian Decision Processes with Uncertain Transition Probabilities
• Robust Markov Decision Processes with Data-Driven, Distance-Based Ambiguity Sets
• Robust Markov Decision Processes
• Robust Control of Markov Decision Processes with Uncertain Transition Matrices
• Robust Dynamic Programming

This page was built for publication: A family of \(s\)-rectangular robust MDPs: relative conservativeness, asymptotic analyses, and finite-sample properties