Publication:3926044
From MaRDI portal
zbMath0471.68034MaRDI QIDQ3926044
Publication date: 1981
absolute expediency; ergodic learning algorithms; control of a Markov chain; perfect cooperative games; two persons zero sum stochastic games with incomplete and imperfect informations
68T05: Learning and adaptive systems in artificial intelligence
68Q45: Formal languages and automata
60J20: Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.)
68-02: Research exposition (monographs, survey articles) pertaining to computer science
91A60: Probabilistic games; gambling
60-02: Research exposition (monographs, survey articles) pertaining to probability theory
Related Items
Stochastic automata and learning systems., Pioneering approaches for enhancing the speed of hierarchical LA by \textit{ordering} the actions, An Adaptive Learning Game Model for Interacting Electric Power Markets, A cooperative game of a pair of learning automata, On conditional optimality of a class of learning automata in random environments, Learning models for decentralized decision making, Asymptotic behavior of a hierarchical system of learning automata, Multiaction learning automata possessing ergodicity of the mean, A hierarchical system of learning automata that can learn the globally optimal path, Learning algorithms for repeated bimatrix Nash games with incomplete information, On product nonlinearities in stochastic differential equations, epsilon-optimality of a general class of learning algorithms, A novel technique for stochastic root-finding: enhancing the search with adaptive \(d\)-ary search, Stochastic learning-based weak estimation of multinomial random variables and its applications to pattern recognition in non-stationary environments, Intelligent sensory evaluation: Concepts, implementations, and applications, A learning automata based algorithm for optimization of continuous complex functions, Time to absorption in discounted reinforcement models., Achieving Unbounded Resolution inFinitePlayer Goore Games Using Stochastic Automata, and Its Applications, AN ESTIMATOR ALGORITHM FOR LEARNING AUTOMATA WITH CHANGING NUMBER OF ACTIONS, Asymptotic behaviour of a learning algorithm, Learning behaviours of hierarchical structure stochastic automata operating in a non-stationary multi-teacher environment, Modelling and learning control of rotary phosphate dryer