Behavioral Economics Commons^™

A Unified Model Of Adaptive Learning In Normal Form Games, Naoki Funai

Naoki Funai

We investigate an adaptive learning model which nests several existing learning models such as payoff assessment learning, valuation learning, stochastic fictitious play learning, experience-weighted attraction learning and delta learning with indirect payoff information in normal form games. In this paper, we consider adaptive players each of whom (i) assigns payoff assessments to his own actions, (ii) chooses an action which has the highest assessment with some perturbations, and (iii) updates the assessments using observed payoffs, which may include payoffs from unchosen actions, in each period. Utilising the asynchronous stochastic approximation method introduced by Tsitsiklis (1994), we provide conditions under which …