Approximate receding horizon approach for Markov decision processes: average reward case

DOI10.1016/S0022-247X(03)00506-7zbMath1064.90051MaRDI QIDQ1414220

Hyeong Soo Chang, Steven I. Marcus

Publication date: 20 November 2003

Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)

zbMATH Keywords

ergodicityMarkov decision processreceding horizon controlpolicy improvementInfinite-horizon average reward

Mathematics Subject Classification ID

Decision theory (91B06) Markov and semi-Markov decision processes (90C40)

Related Items

Attention allocation for decision making queues ⋮ On Bellman's principle with inequality constraints ⋮ A policy improvement method for constrained average Markov decision processes ⋮ Anticipation of goals in automated planning ⋮ Multi-policy improvement in stochastic optimization with forward recursive function criteria ⋮ An AO^* Based Exact Algorithm for the Canadian Traveler Problem ⋮ A perturbation approach to approximate value iteration for average cost Markov decision processes with Borel spaces and bounded costs ⋮ Approximation of average cost Markov decision processes using empirical distributions and concentration inequalities

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• An on-line procedure in discounted infinite-horizon stochastic optimal control
• Optimal infinite-horizon feedback laws for a general class of constrained discrete-time systems: Stability and moving-horizon approximations
• A forecast horizon and a stopping rule for general Markov decision processes
• Enlarging the region of convergence of Newton's method for constrained optimization
• Separable routing: A scheme for state-dependent routing of circuit switched telephone traffic
• On the value function of a priority queue with an application to a controlled polling model
• Comparing neuro-dynamic programming algorithms for the vehicle routing problem with stochastic demands
• Adaptive Markov control processes
• Rollout algorithms for stochastic scheduling problems
• Receding horizon control of nonlinear systems
• Complexity of finite-horizon Markov decision process problems
• Optimal Infinite-Horizon Undiscounted Control of Finite Probabilistic Systems
• The Determination of Approximately Optimal Policies in Markov Decision Processes by the Use of Bounds
• Finite horizon approximations of infinite horizon linear programs
• The policy iteration algorithm for average reward Markov decision processes with general state space
• On the structure of value functions for threshold policies in queueing models
• A probabilistic analysis of bias optimality in unichain Markov decision processes
• Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
• Error bounds for rolling horizon policies in discrete-time Markov control processes
• Detection of minimal forecast horizons in dynamic programs with multiple indicators of the future
• Moving horizon control in dynamic games