Robust MDPs with k-rectangular uncertainty

DOI10.1287/MOOR.2016.0786zbMATH Open1349.90833OpenAlexW2553297237MaRDI QIDQ2833114FDOQ2833114

Huan Xu, Ofir Mebel, Shie Mannor

Publication date: 16 November 2016

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1287/moor.2016.0786

zbMATH Keywords

dynamic programmingoptimal controlmodelsMarkov

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Cites Work

• Risk, ambiguity and the Savage axioms
• The Price of Robustness
• Probability Inequalities for the Sum of Independent Random Variables
• Learning Under Ambiguity
• Robust convex optimization
• Distributionally Robust Optimization and Its Tractable Approximations
• Robust Control of Markov Decision Processes with Uncertain Transition Matrices
• Robust Dynamic Programming
• Extending scope of robust optimization: comprehensive robust counterparts of uncertain problems
• Percentile Optimization for Markov Decision Processes with Parameter Uncertainty
• Risk-averse dynamic programming for Markov decision processes
• Near-optimal regret bounds for reinforcement learning
• Robust Markov Decision Processes
• Bounded-parameter Markov decision processes
• Bias and Variance Approximation in Value Function Estimates
• Distributionally robust Markov decision processes
• A Convex Analytic Approach to Risk-Aware Markov Decision Processes
• Robust Adaptive Markov Decision Processes: Planning with Model Uncertainty

Cited In (11)

• A dynamical neural network approach for distributionally robust chance-constrained Markov decision process
• A survey of decision making and optimization under uncertainty
• Robust \(Q\)-learning algorithm for Markov decision processes under Wasserstein uncertainty
• Policy-based branch-and-bound for infinite-horizon multi-model Markov decision processes
• Concurrent MDPs with Finite Markovian Policies
• A family of \(s\)-rectangular robust MDPs: relative conservativeness, asymptotic analyses, and finite-sample properties
• Set-based value operators for non-stationary and uncertain Markov decision processes
• Title not available (Why is that?)
• Robust Markov Decision Processes with Data-Driven, Distance-Based Ambiguity Sets
• Distributionally Robust Partially Observable Markov Decision Process with Moment-Based Ambiguity
• Infinite Horizon Average Cost Dynamic Programming Subject to Total Variation Distance Ambiguity

Uses Software

• ROME

This page was built for publication: Robust MDPs with \(k\)-rectangular uncertainty

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2833114)