Use of Stochastic Automata for Parameter Self-Optimization with Multimodal Performance Criteria

DOI10.1109/TSSC.1969.300228zbMATH Open0184.19401MaRDI QIDQ5575971FDOQ5575971

Authors: I. J. Shapiro, K. S. Narendra 

Publication date: 1969

Published in: IEEE Transactions on Systems Science and Cybernetics (Search for Journal in Brave)

zbMATH Keywords

control theory

Cited In (23)

• Achieving Unbounded Resolution inFinitePlayer Goore Games Using Stochastic Automata, and Its Applications
• When can the two-armed bandit algorithm be trusted?
• Theoretical considerations of the parameter self-optimization by stochastic automata
• On ergodic two-armed bandits
• A learning automata based algorithm for optimization of continuous complex functions
• A strategy for controlling nonlinear systems using a learning automaton
• An application of the stochastic automaton to the investment game
• Probabilistic automata
• Convergence in models with bounded expected relative hazard rates
• Combinatorial optimization by stochastic automata
• A cooperative game of a pair of learning automata
• epsilon-optimality of a general class of learning algorithms
• Nonconvergence to saddle boundary points under perturbed reinforcement learning
• Optimal non-linear reinforcement schemes for stochastic automata
• Distributed dynamic reinforcement of efficient outcomes in multiagent coordination and network formation
• On conditional optimality of a class of learning automata in random environments
• How Fast Is the Bandit?
• Learning automata algorithms for pattern classification.
• Stochastic automata and learning systems.
• Learning behavior of stochastic automata in the last stage of learning
• Choice of optimal subset of numbers using a learning automaton
• Reinforcement learning with internal expectation for the random neural network
• Regret bounds for Narendra-Shapiro bandit algorithms

This page was built for publication: Use of Stochastic Automata for Parameter Self-Optimization with Multimodal Performance Criteria

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5575971)