Percentile Optimization for Markov Decision Processes with Parameter Uncertainty

DOI10.1287/OPRE.1080.0685zbMATH Open1226.90128OpenAlexW2165622730MaRDI QIDQ3100462FDOQ3100462

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

value at riskstochastic programmingMarkov decision processesparameter uncertaintychance-constrained optimizationfinite statestochastic model applications

Mathematics Subject Classification ID

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

Cited In (32)

• Robust topological policy iteration for infinite horizon bounded Markov decision processes
• Robust Markov control processes
• Approximability and efficient algorithms for constrained fixed-horizon POMDPs with durative actions
• A dynamical neural network approach for distributionally robust chance-constrained Markov decision process
• Quantile Markov Decision Processes
• Variance-constrained actor-critic algorithms for discounted and average reward MDPs
• Ambiguous partially observable Markov decision processes: structural results and applications
• Distributionally robust chance constraints for non-linear uncertainties
• Percentile queries in multi-dimensional Markov decision processes
• Distributionally robust chance-constrained Markov decision processes with random payoff
• Profit criteria involving risk in price setting of virtual products
• BOUNDED-PARAMETER PARTIALLY OBSERVABLE MARKOV DECISION PROCESSES: FRAMEWORK AND ALGORITHM
• Robust control of the multi-armed bandit problem
• Policy-based branch-and-bound for infinite-horizon multi-model Markov decision processes
• Robust analysis of discounted Markov decision processes with uncertain transition probabilities
• Towards Min Max Generalization in Reinforcement Learning
• Partially observable Markov decision processes incorporating
• Bounding fixed points of set-based Bellman operator and Nash equilibria of stochastic games
• Reinforcement learning with dynamic convex risk measures
• Multi-stage distributionally robust convex stochastic optimization with Bayesian-type ambiguity sets
• A percentile system optimization approach with and without path enumeration
• Optimal Information Blending with Measurements in the L² Sphere
• Robust MDPs with \(k\)-rectangular uncertainty
• Percentile optimization in multi-armed bandit problems
• Constrained Markov decision processes with uncertain costs
• A family of \(s\)-rectangular robust MDPs: relative conservativeness, asymptotic analyses, and finite-sample properties
• Probabilistic Guarantees in Robust Optimization
• Distributionally robust optimization for sequential decision-making
• Data-driven remanufacturing planning with parameter uncertainty
• Joint chance-constrained Markov decision processes
• Robust Markov Decision Processes with Data-Driven, Distance-Based Ambiguity Sets
• Distributionally Robust Partially Observable Markov Decision Process with Moment-Based Ambiguity

Recommendations

• Title not available (Why is that?) 👍 👎
• Title not available (Why is that?) 👍 👎
• Percentile performance criteria for limiting average Markov decision processes 👍 👎
• Partially observable Markov decision processes with imprecise parameters 👍 👎
• Optimality Conditions for Partially Observable Markov Decision Processes 👍 👎
• Percentile queries in multi-dimensional Markov decision processes 👍 👎
• Optimization under Decision-Dependent Uncertainty 👍 👎
• Optimization of Markov decision processes under the variance criterion 👍 👎
• Percentile queries in multi-dimensional Markov decision processes 👍 👎
• Optimization in periodic Markovian decision processes 👍 👎

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3100462)