Template-Type: ReDIF-Paper 1.0
Author-Name: Waltman, L.
Author-Name-Last: Waltman
Author-Name-First: Ludo
Author-Name: Kaymak, U.
Author-Name-Last: Kaymak
Author-Name-First: Uzay
Author-Person: pka115
Title: A Theoretical Analysis of Cooperative Behavior in Multi-Agent Q-learning
Abstract: A number of experimental studies have investigated whether cooperative behavior may emerge in multi-agent Q-learning. In some studies cooperative behavior did emerge, in others it did not. This report provides a theoretical analysis of this issue. The analysis focuses on multi-agent Q-learning in iterated prisoner’s dilemmas. It is shown that under certain assumptions cooperative behavior may emerge when multi-agent Q-learning is applied in an iterated prisoner’s dilemma. An important consequence of the analysis is that multi-agent Q-learning may result in non-Nash behavior. It is found experimentally that the theoretical results derived in this report are quite robust to violations of the underlying assumptions.
Creation-Date: 2006-02-01
File-URL: https://repub.eur.nl/pub/7323/ERS%202006%20006%20LIS.pdf
File-Format: application/pdf
Series: RePEc:ems:eureri
Number: ERS-2006-006-LIS
Classification-JEL: C51, L15, M, O32
Keywords: Cooperation, Multi-Agent Q-Learning, Multi-Agent Reinforcement Learning, Nash Equilibrium, Prisoner’s Dilemma
Handle: RePEc:ems:eureri:7323