Learning algorithms for Markov decision processes

DOI10.2307/3214080MaRDI QIDQ3768706zbMATH OpenOpenAlexFDO

Authors Masami Kurano

Publication date 1987

Published in Journal of Applied Probability (Search for Journal in Brave)

Full work available at URL https://doi.org/10.2307/3214080

zbMATH Keywords

adaptive controlaverage rewardlearning algorithmsrelaxationunknown transition lawfinite Markov decision chainunknown random one stage rewards

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Recommendations

• Learning algorithms for finite horizon constrained Markov decision processes
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• Learning Policies for Markov Decision Processes From Data
• Learning algorithms for Markov decision processes with average cost
• Reinforcement learning based algorithms for average cost Markov decision processes
• Reinforcement learning in robust Markov decision processes
• Reinforcement learning of non-Markov decision processes
• Recursive Learning Automata Approach to Markov Decision Processes
• Learning algorithms for discounted MDPs with constraints

Cited in

(17)

• \(L^\ast\)-based learning of Markov decision processes (extended version)
• scientific article; zbMATH DE number 9347 (Why is no real title available?)
• A unified approach to adaptive control of average reward Markov decision processes
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• Learning Variable-Length Markov Models of Behavior
• Central limit theorem for the estimator of the value of an optimal stopping problem
• Adaptive policy-iteration and policy-value-iteration for discounted Markov decision processes
• Adaptive control of Markov chains with local updates
• scientific article; zbMATH DE number 3898638 (Why is no real title available?)
• Computationally efficient algorithms for on-line optimization of Markov decision processes
• A learning algorithm for communicating Markov decision processes with unknown transition matrices
• Learning algorithms for finite horizon constrained Markov decision processes
• Markov decision processes with arbitrary reward processes
• Q-learning for Markov decision processes with a satisfiability criterion
• Learning parametric policies and transition probability models of Markov decision processes from data
• Decentralized learning in finite Markov chains
• Statistical inference for a finite optimal stopping problem with unknown transition probabilities

This page was built for publication: Learning algorithms for Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3768706)