Robust MDPs with k-rectangular uncertainty

DOI10.1287/MOOR.2016.0786MaRDI QIDQ2833114zbMATH OpenOpenAlexFDO

Authors Shie Mannor, Ofir Mebel, Huan Xu

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 programmingMarkovmodelsoptimal control

Mathematics Subject Classification ID

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

Recommendations

• Robust Markov Decision Processes
• Distributionally robust Markov decision processes
• Reinforcement learning in robust Markov decision processes
• Robust Control of Markov Decision Processes with Uncertain Transition Matrices
• Distributionally robust optimization for sequential decision-making

Cites work

• A convex analytic approach to risk-aware Markov decision processes
• Bias and variance approximation in value function estimates
• Bounded-parameter Markov decision processes
• Distributionally robust Markov decision processes
• Distributionally robust optimization and its tractable approximations
• Extending scope of robust optimization: comprehensive robust counterparts of uncertain problems
• Learning Under Ambiguity
• Near-optimal regret bounds for reinforcement learning
• Percentile Optimization for Markov Decision Processes with Parameter Uncertainty
• Probability Inequalities for the Sum of Independent Random Variables
• Risk, ambiguity and the Savage axioms
• Risk-averse dynamic programming for Markov decision processes
• Robust Adaptive Markov Decision Processes: Planning with Model Uncertainty
• Robust Control of Markov Decision Processes with Uncertain Transition Matrices
• Robust convex optimization
• Robust Dynamic Programming
• Robust Markov Decision Processes
• The Price of Robustness

Cited in

(18)

• Policy-based branch-and-bound for infinite-horizon multi-model Markov decision processes
• A survey of decision making and optimization under uncertainty
• Reinforcement learning in robust Markov decision processes
• Robust decomposable Markov decision processes motivated by allocating school budgets
• Concurrent MDPs with Finite Markovian Policies
• scientific article; zbMATH DE number 7626790 (Why is no real title available?)
• 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
• Robust Markov Decision Processes: Beyond Rectangularity
• A family of \(s\)-rectangular robust MDPs: relative conservativeness, asymptotic analyses, and finite-sample properties
• A dynamical neural network approach for distributionally robust chance-constrained Markov decision process
• Robust Q-learning algorithm for Markov decision processes under Wasserstein uncertainty
• Set-based value operators for non-stationary and uncertain Markov decision processes
• Policy gradient algorithms for robust MDPs with nonrectangular uncertainty sets
• Bounding the difference between the values of robust and non-robust Markov decision problems
• Sequential decision-making under uncertainty: a robust MDPs review
• Solution for infinite horizon double-factored Markov decision processes with application

Describes a project that uses

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)