Modelling the Dynamics of Multiagent Q-Learning in Repeated Symmetric Games: a Mean Field Theoretic Approach

Shuyue Hu
Shuyue Hu
Chin-wing Leung
Chin-wing Leung

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), pp. 12102-12112, 2019.

Cited by: 0|Views17
EI

Abstract:

Modelling the dynamics of multi-agent learning has long been an important research topic, but all of the previous works focus on 2-agent settings and mostly use evolutionary game theoretic approaches. In this paper, we study an n-agent setting with n tends to infinity, such that agents learn their policies concurrently over repeated symme...More

Code:

Data:

Your rating :
0

 

Tags
Comments