Some convergence theorems for stochastic learning models with distance diminishing operators

DOI10.1016/0022-2496(68)90058-8zbMath0155.29303OpenAlexW2054901429MaRDI QIDQ2527123

M. Frank Norman

Publication date: 1968

Published in: Journal of Mathematical Psychology (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0022-2496(68)90058-8

zbMATH Keywords

mathematical biology

Related Items (24)

Adaptive learning via selectionism and Bayesianism. I: Connection between the two ⋮ Stochastic approximation to understand simple simulation models ⋮ Bayesian learning behaviour and the stability of equilibrium forecasts ⋮ Learning through reinforcement and replicator dynamics ⋮ Zur Erlernung optimalen Verhaltens in Entscheidungssituationen ⋮ Categorical time semes with a recursive scheme and with covariates ⋮ On a general class of absorbing-barrier learning algorithms ⋮ On learning dynamics underlying the evolution of learning rules ⋮ Transient and asymptotic dynamics of reinforcement learning in games ⋮ Cantor coding in the hippocampus ⋮ FRACTALS, SEMIFRACTALS AND MARKOV OPERATORS ⋮ Bayesian games as stochastic processes ⋮ Functions of event variables of a random system with complete connections ⋮ Sequential games as stochastic processes ⋮ On the linear model with two absorbing barriers ⋮ Asymptotic properties of monotonic learning models ⋮ A central limit theorem for families of stochastic processes indexed by a small average step size parameter, and some applications to learning models ⋮ Strongly mixing g-measures ⋮ Reinforcement learning with internal expectation for the random neural network ⋮ Hypotheses on the functional roles of chaotic transitory dynamics ⋮ Adaptive approaches to stochastic programming ⋮ Multiaction learning automata possessing ergodicity of the mean ⋮ A myopic adjustment process leading to best-reply matching. ⋮ On a theorem of Karlin

Cites Work

• A convergence theorem for a certain class of Markoff processes
• Chains of infinite order and their application to learning theory
• Asymptotic behavior of successive iterates of continuous functions under a Markov operator
• Correction to 'Chains of infinite order and their application to learning theory'
• Incremental learning on random trials
• Probability learning with noncontingent success
• Théorie ergodique pour des classes d'opérations non completement continues
• Some random walks arising in learning models. I
• On A Class of Operators Occurring in the Theory of Chains of Infinite Order
• The Strong Law of Large Numbers for a Class of Markov Chains
• Finite Continuous Time Markov Chains
• Ergodic Decompositions Induced by Certain Markov Operators
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Some convergence theorems for stochastic learning models with distance diminishing operators