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

DOI10.1137/21M1423841zbMATH Open1493.90215OpenAlexW4280617966MaRDI QIDQ5081099FDOQ5081099

Authors: Sivaramakrishnan Ramani, Archis Ghate 

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

Recommendations

• Distributionally robust partially observable Markov decision process with moment-based ambiguity
• Distributionally robust Markov decision processes
• Robust Markov Decision Processes
• Distributionally Robust Counterpart in Markov Decision Processes
• Robust Adaptive Markov Decision Processes: Planning with Model Uncertainty
• Toward theoretical understandings of robust Markov decision processes: sample complexity and asymptotics
• Ambiguous partially observable Markov decision processes: structural results and applications
• Robust analysis of discounted Markov decision processes with uncertain transition probabilities
• Markov decision processes under ambiguity
• Distributionally Robust Markov Decision Processes and Their Connection to Risk Measures

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)

Cites Work

• Title not available (Why is that?)
• On Choosing and Bounding Probability Metrics
• Title not available (Why is that?)
• Ambiguous chance constrained problems and robust optimization
• Distributionally robust optimization under moment uncertainty with application to data-driven problems
• On the rate of convergence in Wasserstein distance of the empirical measure
• Title not available (Why is that?)
• Distributionally robust optimization and its tractable approximations
• Robust Control of Markov Decision Processes with Uncertain Transition Matrices
• Robust Dynamic Programming
• Minimax Control of Discrete-Time Stochastic Systems
• Data-driven chance constrained stochastic program
• Percentile Optimization for Markov Decision Processes with Parameter Uncertainty
• Robust portfolio control with stochastic factor dynamics
• Robust assortment optimization in revenue management under the multinomial logit choice model
• On a Class of Minimax Stochastic Programs
• A sharp estimate of the binomial mean absolute deviation with applications
• Robust Markov Decision Processes
• Markovian Decision Processes with Uncertain Transition Probabilities
• Data-driven risk-averse stochastic optimization with Wasserstein metric
• Distributionally Robust Convex Optimization
• Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
• Risk-averse two-stage stochastic program with distributional ambiguity
• Robust sample average approximation
• Wasserstein Distributionally Robust Stochastic Control: A Data-Driven Approach
• Distributionally robust optimization with decision dependent ambiguity sets
• Robust MDPs with \(k\)-rectangular uncertainty
• Distributionally Robust Stochastic Dual Dynamic Programming
• Distributionally robust optimization for sequential decision-making
• 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
• Infinite Horizon Average Cost Dynamic Programming Subject to Total Variation Distance Ambiguity
• Dynamic programming subject to total variation distance ambiguity

Cited In (10)

• Robust topological policy iteration for infinite horizon bounded Markov decision processes
• A dynamical neural network approach for distributionally robust chance-constrained Markov decision process
• Ambiguous partially observable Markov decision processes: structural results and applications
• Performance guarantees for empirical Markov decision processes with applications to multiperiod inventory models
• Distributionally robust Markov decision processes
• Distributionally robust partially observable Markov decision process with moment-based ambiguity
• Robust \(Q\)-learning algorithm for Markov decision processes under Wasserstein uncertainty
• Reinforcement learning in robust Markov decision processes
• A family of \(s\)-rectangular robust MDPs: relative conservativeness, asymptotic analyses, and finite-sample properties
• Distributionally robust optimization for sequential decision-making

Uses Software

• ROME

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5081099)