Skip to main content Accessibility help
×
Hostname: page-component-7b7567c8c-z4zkx Total loading time: 0 Render date: 2026-11-17T14:48:42.755Z Has data issue: false hasContentIssue false

22 - Learning and Equilibrium Refinements

from Part V - Economics And Institutional Design

Published online by Cambridge University Press:  03 March 2026

Get access

Summary

The literature on learning in games interprets equilibrium strategy profiles as the long-run average behavior of agents who are selected at random to play the game. As suggested by Nash, in normal-form games we expect that as the agents accumulate evidence about play of the game they will develop accurate beliefs, so that the stationary points of the process correspond to the Nash equilibria. The definition of Nash equilibrium applies unchanged to games in extensive form, but the learning foundation for it does change, because in games with a nontrivial extensive form simply playing the game repeatedly may not lead agents to know how their opponents would respond to deviations that the agents have not tried. Thus there is no reason to expect learning by myopic agents to lead to Nash equilibrium in general games, as agents may not experiment enough to learn the consequences of deviating from the equilibrium path. Instead, learning is consistent with self-confirming equilibrium, introduced by Fudenberg and Levine in the early 1990s. The focus here is on settings where the agents are patient, so they do have an incentive to experiment. In this case, Nash’s mass action interpretation of equilibrium is again valid. But extensive-form games typically have many equilibria, and not all of them seem equally plausible. An advantage of the learning approach is that some actions that are off-path according to the limiting equilibrium distribution are not counterfactual, but will actually be played by young agents as “experiments,” so that equilibrium refinements can be derived from properties of optimal experimentation.

Information

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Book purchase

Temporarily unavailable

Save book to Kindle

To save this book to your Kindle, first ensure no-reply@cambridge.org is added to your Approved Personal Document E-mail List under your Personal Document Settings on the Manage Your Content and Devices page of your Amazon account. Then enter the ‘name’ part of your Kindle email address below. Find out more about saving to your Kindle.

Note you can select to save to either the @free.kindle.com or @kindle.com variations. ‘@free.kindle.com’ emails are free but can only be saved to your device when it is connected to wi-fi. ‘@kindle.com’ emails can be delivered even when you are not connected to wi-fi, but note that service fees apply.

Find out more about the Kindle Personal Document Service.

Available formats
×

Save book to Dropbox

To save content items to your account, please confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your account. Find out more about saving content to Dropbox.

Available formats
×

Save book to Google Drive

To save content items to your account, please confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your account. Find out more about saving content to Google Drive.

Available formats
×