Optimal action criterion and algorithm improvement of real-time dynamic programming

MaRDI QIDQ3406314zbMATH OpenFDO

Authors Changjie Fan, Xiaoping Chen

Publication date 12 February 2010

zbMATH Keywords

convergence criterionheuristic searchincremental solvingMarkov decision processreal-time dynamic programming

Mathematics Subject Classification ID

Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Dynamic programming (90C39)

Recommendations

• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• A constrained optimization perspective on actor-critic algorithms and application to network routing
• A policy improvement method for constrained average Markov decision processes
• Real-time dynamic programming for Markov decision processes with imprecise probabilities
• Real-time decision making for large POMDPs

Cited in

(1)

• Real-time decision making for large POMDPs

This page was built for publication: Optimal action criterion and algorithm improvement of real-time dynamic programming

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3406314)