Learning Automata - A Survey

Stochastic automata operating in an unknown random environment have been proposed earlier as models of learning. These automata update their action probabilities in accordance with the inputs received from the environment and can improve their own performance during operation. In this context they are referred to as learning automata. A survey of the available results in the area of learning automata has been attempted in this paper. Attention has been focused on the norms of behavior of learning automata, issues in the design of updating schemes, convergence of the action probabilities, and interaction of several automata. Utilization of learning automata in parameter optimization and hypothesis testing is discussed, and potential areas of application are suggested.

[1]  R. Duncan Luce,et al.  Individual Choice Behavior , 1959 .

[2]  M. L. Tsetlin.  On the Behavior of Finite Automata in Random Media , 1961 .

[3]  R. W. Mclaren,et al.  A stochastic automaton model for the synthesis of learning systems , 1966 .

[4]  J. Sklansky,et al.  Learning systems for automatic control , 1966 .

[5]  Balakrishnan Chandrasekaran,et al.  Adaptation of stochastic automata in nonstationary environments , 1967 .

[6]  B. Chandrasekaran,et al.  On Expediency and Convergence in Variable-Structure Automata , 1968, IEEE Trans. Syst. Sci. Cybern..

[7]  M. Norman.  Some convergence theorems for stochastic learning models with distance diminishing operators , 1968 .

[8]  M. Norman.  On the linear model with two absorbing barriers , 1968 .

[9]  Kumpati S. Narendra,et al.  Use of Stochastic Automata for Parameter Self-Optimization with Multimodal Performance Criteria , 1969, IEEE Trans. Syst. Sci. Cybern..

[10]  King-Sun Fu,et al.  Formulation of learning automata and automata games , 1969, Inf. Sci..

[11]  J. Spruce Riordon,et al.  An adaptive automaton controller for discrete-time markov processes , 1969, Autom..

[12]  J. Riordon.  Optimal feedback characteristics from stochastic automaton models , 1969 .

[13]  King-Sun Fu,et al.  On stochastic automata and languages , 1969, Inf. Sci..

[14]  Brian R. Gaines,et al.  Stochastic Computing Systems , 1969 .

[15]  B. Chandrasekaran,et al.  Stochastic Automata Games , 1969, IEEE Trans. Syst. Sci. Cybern..

[16]  Thomas M. Cover,et al.  The two-armed-bandit problem with time-invariant finite memory , 1970, IEEE Trans. Inf. Theory.

[17]  King-Sun Fu,et al.  On search techniques in switching environments , 1970 .

[18]  King-Sun Fu,et al.  Learning control systems--Review and outlook , 1970 .

[19]  Ray A. Jarvis,et al.  Adaptive Global Search in a Time-Variant Environment Using a Probabilistic Automaton with Pattern Recognition Supervision , 1970, IEEE Trans. Syst. Sci. Cybern..

[20]  Robert M. Glorioso,et al.  A Training Algorithm for Systems Described by Stochastic Transition Matrices , 1971, IEEE Trans. Syst. Man Cybern..

[21]  B. Chandrasekaran,et al.  On dimensionality and sample size in statistical pattern classification , 1971, Pattern Recognit..

[22]  G. Langholz.  Behaviour of automata in a nonstationary random environment , 1971 .

[23]  K. S. Fuf.  Stochastic Automata, Stochastic Languages and Pattern Recognition , 1971 .

[24]  Kumpati S. Narendra,et al.  A two-level system of stochastic automata for periodic random environments , 1971, CDC 1971.

[25]  Ian H. Witten,et al.  Comments on "Use of Stochastic Automata for Parameter Self-Optimization with Multimodal Performance Criteria" , 1972, IEEE Trans. Syst. Man Cybern..

[26]  K. Narendra,et al.  Comparison of Expedient and Optima Reinforcement Schemes for Learning Systems , 1972 .

[27]  V. I. Varahavsky.  Automata Games and Control Problems , 1972 .

[28]  Kumpati S. Narendra,et al.  Stochastic Automata Models with Applications to Learning Systems , 1973, IEEE Trans. Syst. Man Cybern..

[29]  Hidekazu Tsuji,et al.  An automaton in the nonstationary random environment , 1973, Inf. Sci..

[30]  S. Lakshmivarahan,et al.  Absolutely Expedient Learning Algorithms For Stochastic Automata , 1973 .

[31]  Ian H. Witten.  Finite-Time Performance of Some Two-Armed Bandit Controllers , 1973, IEEE Trans. Syst. Man Cybern..

[32]  K. Narendra.  Competitive and Cooperative Games of Variable-Structure Stochastic Automata , 1973 .

[33]  George N. Saridis,et al.  On-line learning control algorithms , 1973 .

[34]  J. Mendel.  Reinforcement learning models and their applications to control problems , 1973 .

[35]  L. Mason,et al.  An optimal learning algorithm for S-model environments , 1973 .

[36]  Kumpati S. Narendra,et al.  Adaptation and learning in automatic systems , 1974 .