On ε-Optimality of the Pursuit Learning Algorithm

DOI10.1239/jap/1346955334zbMath1251.68167MaRDI QIDQ3165495

Ryan Martin, Omkar Tilak

Publication date: 29 October 2012

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

Full work available at URL: https://projecteuclid.org/euclid.jap/1346955334

zbMATH Keywords

convergence; learning automaton; indirect estimator algorithm

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

68W27: Online algorithms; streaming algorithms

68Q87: Probability in computer science (algorithm analysis, random structures, phase transitions, etc.)

Related Items

The design of absorbing Bayesian pursuit algorithms and the formal analyses of their \(\varepsilon\)-optimality

Cites Work

• Clustering the wireless ad hoc networks: a distributed learning automata approach
• An intelligent backbone formation algorithm for wireless ad hoc networks based on distributed learning automata
• Stochastic comparisons of order statistics from heterogeneous populations, with applications in reliability
• Discretized pursuit learning automata
• Stochastic ordering of classical discrete distributions
• A new approach to the design of reinforcement schemes for learning automata
• Learning Optimal Discriminant Functions through a Cooperative Game of Automata
• Learning Automata - A Survey
• Probability Inequalities for Sums of Bounded Random Variables
• A Stochastic Approximation Method
• Unnamed Item
• Unnamed Item