Simulation-based algorithms for Markov decision processes

DOI10.1007/978-1-4471-5022-0zbMath1293.93002OpenAlexW4302608015MaRDI QIDQ1946768

Jiaqiao Hu, Hyeong Soo Chang, Michael C. Fu, Steven I. Marcus

Publication date: 16 April 2013

Published in: Communications and Control Engineering (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-1-4471-5022-0

zbMATH Keywords

simulationMarkov decision processoptimal policymodel reference adaptive searchmulti-stage adaptive samplingpopulation-based evolutionary method

Mathematics Subject Classification ID

Applications of statistics in engineering and industry; control charts (62P30) Approximation methods and heuristics in mathematical programming (90C59) Research exposition (monographs, survey articles) pertaining to systems and control theory (93-02) Markov and semi-Markov decision processes (90C40) Stochastic systems in control theory (general) (93E03)

Related Items (14)

An incremental off-policy search in a model-free Markov decision process using a single sample path ⋮ Risk-Sensitive Reinforcement Learning via Policy Gradient Search ⋮ Random search for constrained Markov decision processes with multi-policy improvement ⋮ Optimal decision-making of mutual fund temporary borrowing problem via approximate dynamic programming ⋮ A rollout algorithm framework for heuristic solutions to finite-horizon stochastic dynamic programs ⋮ An exact iterative search algorithm for constrained Markov decision processes ⋮ Value set iteration for Markov decision processes ⋮ Anticipation of goals in automated planning ⋮ Two-phase selective decentralization to improve reinforcement learning systems with MDP ⋮ CONIC CPPIs ⋮ An Approximation Approach for Response-Adaptive Clinical Trial Design ⋮ Value set iteration for two-person zero-sum Markov games ⋮ A performance-centred approach to optimising maintenance of complex systems ⋮ A perturbation approach to approximate value iteration for average cost Markov decision processes with Borel spaces and bounded costs

This page was built for publication: Simulation-based algorithms for Markov decision processes