chapter  5
20 Pages

A survey of Rule Learning in normal-form games: Dale O. Stahl

The approaches to learning in games include: fully rational learning, I evolutionary game theory and replicator dynamics,2 reinforcement learning and belief learning3 and Rule Learning.4 All except the first and the last belong to the class of dynamic models in which the objects of reinforcement are the actions available to the players in a one-shot game; we will refer to these as "action-reinforcement" learning models.