A convex analytic approach to Markov decision processes

From MaRDI portal
Publication:1093563

DOI10.1007/BF00353877zbMath0628.90090OpenAlexW2004640191MaRDI QIDQ1093563

Vivek S. Borkar

Publication date: 1988

Published in: Probability Theory and Related Fields (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/bf00353877




Related Items (33)

Existence of optimal stationary policies in discounted Markov decision processes: Approaches by occupation measuresConstrained discounted stochastic gamesVector-valued Markov decision processes and the systems of linear inequalitiesLinear programming based optimality conditions and approximate solution of a deterministic infinite horizon discounted optimal control problem in discrete timeConvex analytic approach to constrained discounted Markov decision processes with non-constant discount factorsOn Linear Programming for Constrained and Unconstrained Average-Cost Markov Decision Processes with Countable Action Spaces and Strictly Unbounded CostsLinear programming formulations of deterministic infinite horizon optimal control problems in discrete timeLinear programming formulation of MDPs in countable state space: The multichain caseMarkov control models with unknown random state-action-dependent discount factorsLinear programming formulation of long-run average optimal control problemMarkov decision processes with state-dependent discount factors and unbounded rewards/costsA dynamic analytic method for risk-aware controlled martingale problemsStochastic control for organ donations: a reviewThe Linear Program approach in multi-chain Markov Decision Processes revisitedExtreme Occupation Measures in Markov Decision Processes with an Absorbing StateMarkov decision processes with multiple costsAnalysis of averages over distributions of Markov processesA Convex Programming Approach for Discrete-Time Markov Decision Processes under the Expected Total Reward CriterionAdaptive control of constrained Markov chains: Criteria and policiesErgodic and adaptive control of nearest-neighbor motionsSensitivity of constrained Markov decision processesMaximizing the probability of attaining a target prior to extinctionConstrained discounted Markov decision processes with Borel state spacesRationally Inattentive Control of Markov ProcessesStrong Uniform Value in Gambling Houses and Partially Observable Markov Decision ProcessesLP Formulations of Discrete Time Long-Run Average Optimal Control Problems: The NonErgodic CaseConstrained Markov Decision Processes with Expected Total Reward CriteriaThe Kumar-Becker-Lin scheme revisitedOn structural properties of optimal average cost functions in Markov decision processes with Borel spaces and universally measurable policiesHistory-dependent Evaluations in Partially Observable Markov Decision ProcessA Convex Analytic Approach to Risk-Aware Markov Decision ProcessesDenumerable state stochastic games with limiting average payoffFirst passage Markov decision processes with constraints and varying discount factors



Cites Work


This page was built for publication: A convex analytic approach to Markov decision processes