Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Achieving Socially Optimal Outcomes in Multiagent Systems with Reinforcement Social Learning

Achieving Socially Optimal Outcomes in Multiagent Systems with Reinforcement Social Learning Achieving Socially Optimal Outcomes in Multiagent Systems with Reinforcement Social Learning JIANYE HAO and HO-FUNG LEUNG, The Chinese University of Hong Kong In multiagent systems, social optimality is a desirable goal to achieve in terms of maximizing the global efficiency of the system. We study the problem of coordinating on socially optimal outcomes among a population of agents, in which each agent randomly interacts with another agent from the population each round. Previous work [Hales and Edmonds 2003; Matlock and Sen 2007, 2009] mainly resorts to modifying the interaction protocol from random interaction to tag-based interactions and only focus on the case of symmetric games. Besides, in previous work the agents' decision making processes are usually based on evolutionary learning, which usually results in high communication cost and high deviation on the coordination rate. To solve these problems, we propose an alternative social learning framework with two major contributions as follows. First, we introduce the observation mechanism to reduce the amount of communication required among agents. Second, we propose that the agents' learning strategies should be based on reinforcement learning technique instead of evolutionary learning. Each agent explicitly keeps the record of its current state in its learning http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Autonomous and Adaptive Systems (TAAS) Association for Computing Machinery

Achieving Socially Optimal Outcomes in Multiagent Systems with Reinforcement Social Learning

Download PDF
23 pages

Loading next page...
 
/lp/association-for-computing-machinery/achieving-socially-optimal-outcomes-in-multiagent-systems-with-foBmoZLcx4

References (37)

Publisher
Association for Computing Machinery
Copyright
Copyright © 2013 by ACM Inc.
ISSN
1556-4665
DOI
10.1145/2517329
Publisher site
See Article on Publisher Site

Abstract

Achieving Socially Optimal Outcomes in Multiagent Systems with Reinforcement Social Learning JIANYE HAO and HO-FUNG LEUNG, The Chinese University of Hong Kong In multiagent systems, social optimality is a desirable goal to achieve in terms of maximizing the global efficiency of the system. We study the problem of coordinating on socially optimal outcomes among a population of agents, in which each agent randomly interacts with another agent from the population each round. Previous work [Hales and Edmonds 2003; Matlock and Sen 2007, 2009] mainly resorts to modifying the interaction protocol from random interaction to tag-based interactions and only focus on the case of symmetric games. Besides, in previous work the agents' decision making processes are usually based on evolutionary learning, which usually results in high communication cost and high deviation on the coordination rate. To solve these problems, we propose an alternative social learning framework with two major contributions as follows. First, we introduce the observation mechanism to reduce the amount of communication required among agents. Second, we propose that the agents' learning strategies should be based on reinforcement learning technique instead of evolutionary learning. Each agent explicitly keeps the record of its current state in its learning

Journal

ACM Transactions on Autonomous and Adaptive Systems (TAAS) – Association for Computing Machinery

Published: Sep 1, 2013

There are no references for this article.