A least squares temporal difference actor–critic algorithm with applications to warehouse management

DOI10.1002/NAV.21481MaRDI QIDQ3120552zbMATH OpenOpenAlexFDO

Authors Reza Moazzez Estanjini, Keyong Li, Ioannis Ch. Paschalidis

Publication date 5 March 2019

Published in Naval Research Logistics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1002/nav.21481

zbMATH Keywords

actor-critic algorithmsapproximate dynamic programmingMarkov decision processespartial observabilityvehicle routingwarehouse management

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Recommendations

• Learning in structured MDPs with convex cost functions: improved regret bounds for inventory management
• Least squares temporal difference methods: An analysis under general conditions
• Deep reinforcement learning for inventory control: a roadmap
• A reinforcement learning approach to the stochastic cutting stock problem
• Linear least-squares algorithms for temporal difference learning
• Linear least-squares algorithms for temporal difference learning
• An actor-critic algorithm for constrained Markov decision processes
• Temporal difference-based policy iteration for optimal control of stochastic systems

Cited in

(3)

• Deep reinforcement learning for inventory control: a roadmap
• Neural circuits for learning context-dependent associations of stimuli
• Performance optimization for a class of generalized stochastic Petri nets

This page was built for publication: A least squares temporal difference actor–critic algorithm with applications to warehouse management

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3120552)