Markov Decision Processes with Imprecise Transition Probabilities

From MaRDI portal
Publication:4319762

DOI10.1287/opre.42.4.739zbMath0837.90121OpenAlexW2036931518MaRDI QIDQ4319762

Chelsea C. III White, Hany K. El-Deib

Publication date: 6 February 1995

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

Full work available at URL: https://doi.org/10.1287/opre.42.4.739




Related Items (35)

Partially observable Markov decision processes incorporatingGraphical models for imprecise probabilitiesDynamic programming for deterministic discrete-time systems with uncertain gainReachability analysis of uncertain systems using bounded-parameter Markov decision processesPerfect information two-person zero-sum Markov games with imprecise transition probabilitiesConstrained Markov decision processes with uncertain costsBOUNDED-PARAMETER PARTIALLY OBSERVABLE MARKOV DECISION PROCESSES: FRAMEWORK AND ALGORITHMData-driven remanufacturing planning with parameter uncertaintyCoefficients of ergodicity for Markov chains with uncertain parametersReal-time dynamic programming for Markov decision processes with imprecise probabilitiesJoint chance-constrained Markov decision processesEfficient solutions to factored MDPs with imprecise transition probabilitiesSequential decision making with partially ordered preferencesUsing mathematical programming to solve factored Markov decision processes with imprecise probabilitiesComputation of weighted sums of rewards for concurrent MDPsMarkov decision processesA survey of decision making and optimization under uncertaintyUnnamed ItemRobust planning with incomplete domain modelsDiscrete time Markov chains with interval probabilitiesLight robustness in the optimization of Markov decision processes with uncertain parametersRobust analysis of discounted Markov decision processes with uncertain transition probabilitiesProbabilistic Verification of Uncertain Systems Using Bounded-Parameter Markov Decision ProcessesRobust Adaptive Routing Under UncertaintyIMPRECISE MARKOV CHAINS AND THEIR LIMIT BEHAVIORPartially observable Markov decision processes with imprecise parametersDistributionally robust optimization for sequential decision-makingLearning, risk attitude and hot stoves in restless bandit problemsAn active-set strategy to solve Markov decision processes with good-deal risk measureBounded-parameter Markov decision processesRobust control of the multi-armed bandit problemStochastic dynamics simulation with generalized interval probabilityConcurrent MDPs with Finite Markovian PoliciesSolving factored MDPs using non-homogeneous partitionsGeneralizing Markov decision processes to imprecise probabilities




This page was built for publication: Markov Decision Processes with Imprecise Transition Probabilities