A new approach to the design of reinforcement schemes for learning automata

DOI10.1109/TSMC.1985.6313407zbMath0572.68046OpenAlexW2160575156MaRDI QIDQ3690233

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

Publication date: 1985

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

Full work available at URL: https://doi.org/10.1109/tsmc.1985.6313407

zbMATH Keywords

stochastic automatahierarchy of learning automatamultiteacher environmentoptimal choice of actionsrandom characteristics of the environment

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Formal languages and automata (68Q45)

Related Items (22)

Adaptive learning via selectionism and Bayesianism. I: Connection between the two ⋮ Adaptive learning via selectionism and Bayesianism. II: The sequential case ⋮ On ε-Optimality of the Pursuit Learning Algorithm ⋮ Stochastic learning-based weak estimation of multinomial random variables and its applications to pattern recognition in non-stationary environments ⋮ A job scheduling approach based on a learning automaton for a distributed computing system ⋮ A hierarchical system of learning automata that can learn the globally optimal path ⋮ The multi-armed bandit problem: an efficient nonparametric solution ⋮ Parallel algorithm portfolios with adaptive resource allocation strategy ⋮ Adaptive selection of query execution strategies by learning automata ⋮ Reinforcement learning: exploration-exploitation dilemma in multi-agent foraging task ⋮ A strategy for controlling nonlinear systems using a learning automaton ⋮ Reinforcement learning and evolutionary algorithms for non-stationary multi-armed bandit problems ⋮ Optimization based on a team of automata with binary outputs ⋮ A modification of the stochastic ruler method for discrete stochastic optimization ⋮ Stochastic automata and learning systems. ⋮ Learning automata algorithms for pattern classification. ⋮ Simple statistical gradient-following algorithms for connectionist reinforcement learning ⋮ A new continuous action-set learning automaton for function optimization ⋮ A learning automata based algorithm for optimization of continuous complex functions ⋮ An Introduction to Learning Automata and Optimization ⋮ Absorbing stochastic estimator learning automata for S-model stationary environments ⋮ Multi-modal parameter optimization by the automata approach

This page was built for publication: A new approach to the design of reinforcement schemes for learning automata