Robust Markov Decision Processes with Data-Driven, Distance-Based Ambiguity Sets

DOI10.1137/21M1423841zbMath1493.90215OpenAlexW4280617966MaRDI QIDQ5081099

Archis Ghate, Sivaramakrishnan Ramani

Publication date: 1 June 2022

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

Full work available at URL: https://doi.org/10.1137/21m1423841

zbMATH Keywords

dynamic programmingdistributionally robust optimizationvalue convergenceprobabilistic performance guarantees

Mathematics Subject Classification ID

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

Uses Software

• ROME

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Data-driven chance constrained stochastic program
• On the rate of convergence in Wasserstein distance of the empirical measure
• Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
• Robust sample average approximation
• A sharp estimate of the binomial mean absolute deviation with applications
• Distributionally robust optimization with decision dependent ambiguity sets
• Data-driven risk-averse stochastic optimization with Wasserstein metric
• Ambiguous chance constrained problems and robust optimization
• Robust MDPs with k-Rectangular Uncertainty
• Distributionally Robust Convex Optimization
• Distributionally Robust Optimization Under Moment Uncertainty with Application to Data-Driven Problems
• Distributionally Robust Optimization and Its Tractable Approximations
• Percentile Optimization for Markov Decision Processes with Parameter Uncertainty
• Robust Assortment Optimization in Revenue Management Under the Multinomial Logit Choice Model
• Minimax Control of Discrete-Time Stochastic Systems
• On a Class of Minimax Stochastic Programs
• Markovian Decision Processes with Uncertain Transition Probabilities
• On Choosing and Bounding Probability Metrics
• Wasserstein Distributionally Robust Stochastic Control: A Data-Driven Approach
• Distributionally Robust Stochastic Dual Dynamic Programming
• Risk-Averse Two-Stage Stochastic Program with Distributional Ambiguity
• Concentration inequalities for the empirical distribution of discrete distributions: beyond the method of types
• Distributionally Robust Partially Observable Markov Decision Process with Moment-Based Ambiguity
• Robust Portfolio Control with Stochastic Factor Dynamics
• Robust Markov Decision Processes
• Infinite Horizon Average Cost Dynamic Programming Subject to Total Variation Distance Ambiguity
• Distributionally robust optimization for sequential decision-making
• Robust Control of Markov Decision Processes with Uncertain Transition Matrices
• Dynamic Programming Subject to Total Variation Distance Ambiguity
• Robust Dynamic Programming

This page was built for publication: Robust Markov Decision Processes with Data-Driven, Distance-Based Ambiguity Sets