Distributed dynamic programming

DOI10.1109/TAC.1982.1102980MaRDI QIDQ3955990zbMATH OpenOpenAlexFDO

Authors Dimitri P. Bertsekas

Publication date 1982

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/tac.1982.1102980

zbMATH Keywords

decentralizationdistributed computational algorithmsscheduling of computationshortest path problem

Mathematics Subject Classification ID

Existence of optimal solutions to problems involving randomness (49J55) Dynamic programming in optimal control and differential games (49L20) Decomposition methods (49M27) Numerical mathematical programming methods (65K05) Analysis of algorithms and problem complexity (68Q25) Dynamic programming (90C39) Optimal stochastic control (93E20)

Cited in

(22)

• Distributed supply chain management using ant colony optimization
• Model-based average reward reinforcement learning
• Computationally efficient algorithms for on-line optimization of Markov decision processes
• Robust topological policy iteration for infinite horizon bounded Markov decision processes
• Parallel decomposition of multistage stochastic programming problems
• Parallel asynchronous label-correcting methods for shortest paths
• Asynchronous gradient algorithms for a class of convex separable network flow problems
• Robust event-driven interactions in cooperative multi-agent learning
• Approximate policy iteration: a survey and some new methods
• Robust shortest path planning and semicontractive dynamic programming
• Quicker Convergence for Iterative Numerical Solutions to Stochastic Problems: Probabilistic Interpretations, Ordering Heuristics, and Parallel Processing
• Distributed asynchronous computation of fixed points
• On the stability of asynchronous iterative processes
• Q-learning and policy iteration algorithms for stochastic shortest path problems
• A bisection/successive approximation method for computing Gittins indices
• A new class of asynchronous iterative algorithms with order intervals
• A tutorial survey of reinforcement learning
• Independent learning in stochastic games
• Development of a less dissipative interface variable reconstruction to solve the Euler equations by Q learning method
• Extended duality for nonlinear programming
• Some aspects of parallel and distributed iterative algorithms - a survey
• Real-time dynamic programming for Markov decision processes with imprecise probabilities

This page was built for publication: Distributed dynamic programming

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3955990)