Percentile Optimization for Markov Decision Processes with Parameter Uncertainty

DOI10.1287/opre.1080.0685zbMath1226.90128OpenAlexW2165622730MaRDI QIDQ3100462

Erick Delage, Shie Mannor

Publication date: 24 November 2011

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

Full work available at URL: https://semanticscholar.org/paper/29a9e6c5e58232d37ecc7ec8386c5963e54eff05

zbMATH Keywords

stochastic programmingMarkov decision processesparameter uncertaintystochastic model applicationsvalue at riskchance-constrained optimizationfinite state

Mathematics Subject Classification ID

Stochastic programming (90C15) Markov and semi-Markov decision processes (90C40)

Related Items (25)

Ambiguous partially observable Markov decision processes: structural results and applications ⋮ Profit criteria involving risk in price setting of virtual products ⋮ Partially observable Markov decision processes incorporating ⋮ Optimal Information Blending with Measurements in the L² Sphere ⋮ Robust Markov Decision Processes with Data-Driven, Distance-Based Ambiguity Sets ⋮ Bounding fixed points of set-based Bellman operator and Nash equilibria of stochastic games ⋮ Constrained Markov decision processes with uncertain costs ⋮ Quantile Markov Decision Processes ⋮ BOUNDED-PARAMETER PARTIALLY OBSERVABLE MARKOV DECISION PROCESSES: FRAMEWORK AND ALGORITHM ⋮ Robust Markov control processes ⋮ Approximability and efficient algorithms for constrained fixed-horizon POMDPs with durative actions ⋮ Variance-constrained actor-critic algorithms for discounted and average reward MDPs ⋮ Data-driven remanufacturing planning with parameter uncertainty ⋮ Joint chance-constrained Markov decision processes ⋮ Reinforcement learning with dynamic convex risk measures ⋮ Robust topological policy iteration for infinite horizon bounded Markov decision processes ⋮ Distributionally Robust Partially Observable Markov Decision Process with Moment-Based Ambiguity ⋮ Towards Min Max Generalization in Reinforcement Learning ⋮ Policy-based branch-and-bound for infinite-horizon multi-model Markov decision processes ⋮ Robust analysis of discounted Markov decision processes with uncertain transition probabilities ⋮ Distributionally robust chance constraints for non-linear uncertainties ⋮ Robust MDPs with k-Rectangular Uncertainty ⋮ Distributionally robust optimization for sequential decision-making ⋮ Robust control of the multi-armed bandit problem ⋮ Probabilistic Guarantees in Robust Optimization

This page was built for publication: Percentile Optimization for Markov Decision Processes with Parameter Uncertainty