Learning to Play Limited Forecast Equilibria
نویسندگان
چکیده
This paper provides a learning justification for limited forecast equilibria, i.e., Ž . strategy profiles such that 1 players choose their actions in order to maximize the discounted average payoff over their horizon of foresight as given by their forecasts Ž . and 2 forecasts are correct on and off the equilibrium path. The limited forecast equilibria appear to be the stochastically stable outcomes of a simple learning Ž . process involving vanishing trembles. Journal of Economic Literature Classification Numbers: C72, D83. Q 1998 Academic Press
منابع مشابه
Learning in Extensive-Form Games I. Self-Confirming Equilibria
A group of individuals repeatedly plays a fixed extensive-form game, using past play to forecast future actions. Each (asymptotically) maximizes his own immediate expected payoff, believing that others' play corresponds to the historical frequencies of past play. Because players observe only the path of play in each round, they may not learn how others act in parts of the game tree that are not...
متن کاملExistence of Multiagent Equilibria with Limited Agents
Multiagent learning is a necessary yet challenging problem as multiagent systems become more prevalent and environments become more dynamic. Much of the groundbreaking work in this area draws on notable results from game theory, in particular, the concept of Nash equilibria. Learners that directly learn an equilibrium obviously rely on their existence. Learners that instead seek to play optimal...
متن کاملStability of Functional Rational Expectations Equilibria
In this paper we examine a representative agent forecasting prices in a first-order self-referential overlapping generations model. We first consider intermediate stage learning, where agents update the forecasting rule every m periods. We show that, in theory and simulations, the learning rule does not converge to the rational expectations equilibrium (REE). We next consider two stage learning...
متن کاملLearning Dynamics Based on Social Comparisons
We study models of learning in games where agents with limited memory use social information to decide when and how to change their play. When agents only observe the aggregate distribution of payoffs and only recall information from the last period, we show that aggregate play comes close to Nash equilibrium behavior for (generic) games, and that pure equilibria are generally more stable than ...
متن کاملBehavioral learning equilibria
We propose behavioral learning equilibria as a plausible explanation of coordination of individual expectations and aggregate phenomena such as excess volatility in stock prices and high persistence in inflation. Boundedly rational agents use a simple univariate linear forecasting rule and correctly forecast the unconditional sample mean and first-order sample autocorrelation. In the long run, ...
متن کامل