Multi-Agent Reinforcement Learning and Genetic Policy Sharing

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

The effects of policy sharing between agents in a multi-agent dynamical system has not been studied extensively. I simulate a system of agents optimizing the same task using reinforcement learning, to study the effects of different population densities and policy sharing. I demonstrate that sharing policies decreases the time to reach asymptotic behavior, and results in improved asymptotic behavior.
7 pages, 11 figures

Keywords

Multiagent Systems, Artificial Intelligence

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/210017

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/0812.1599
 http://arxiv.org/abs/0812.1599

Collections

arXiv