A hierarchical system of learning automata that can learn the globally optimal path

DOI10.1016/0020-0255(87)90021-1MaRDI QIDQ1096403zbMATH OpenOpenAlexFDO

Authors M. A. L. Thathachar, P. S. Sastry

Publication date 1987

Published in Information Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/0020-0255(87)90021-1

zbMATH Keywords

globally optimal pathhierarchical systemslearning automataMarkov chainsoptimum systems

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Review text

A class of hierarchical systems of learning automata is considered where the system gets responses from its environment at each level of the hierarchy. Hierarchical systems are classified into three types, depending on the nature of the actions constituting the optimal path. If each action is also optimum for the respective level in the hierarchy, then the system is type I. If each action is also optimum for the respective automaton, then the system is type II. Any general hierarchy is type III. It is argued that none of the known reinforcement schemes of learning automata can learn the optimum path in the type III hierarchy. An algorithm for learning the globally optimal path suitable for the most general type of hierarchical problems is presented, and its convergence behavior is examined. The algorithm requires information transfer from the lower levels to the higher levels. The paper cites the connection between the hierarchical model studied and the finite Markov decision processes. No practical application examples are given.

Recommendations

• Asymptotic behavior of a hierarchical system of learning automata
• Analysis of the behaviour of multilevel hierarchical systems of learning automata and their application for multimodal functions optimization
• Learning automata with continuous input and changing number of actions
• scientific article; zbMATH DE number 4037208
• Learning behaviors of hierarchical structure stochastic automata operating in a general multiteacher environment

Cites work

• A Hierarchical System of Learning Automata
• A new approach to the design of reinforcement schemes for learning automata
• Distributed learning of the global maximum in a two-player stochastic game with identical payoffs
• Foundations of the theory of learning systems. Translated by Z. J. Nikolic
• scientific article; zbMATH DE number 3148886 (Why is no real title available?)
• scientific article; zbMATH DE number 3152611 (Why is no real title available?)
• scientific article; zbMATH DE number 3166688 (Why is no real title available?)
• scientific article; zbMATH DE number 4037208 (Why is no real title available?)
• scientific article; zbMATH DE number 3738921 (Why is no real title available?)
• scientific article; zbMATH DE number 3377120 (Why is no real title available?)
• Learning Automata - A Survey
• Learning behaviors of hierarchical structure stochastic automata operating in a general multiteacher environment
• Learning Optimal Discriminant Functions through a Cooperative Game of Automata
• Relaxation Labeling with Learning Automata
• Stochastic Automata Models with Applications to Learning Systems

Cited in

(3)

• Link prediction based on temporal similarity metrics using continuous action set learning automata
• Cellular adaptive Petri net based on learning automata and its application to the vertex coloring problem
• Adaptive learning via selectionism and Bayesianism. II: The sequential case

This page was built for publication: A hierarchical system of learning automata that can learn the globally optimal path

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1096403)