Kagan Tumer's Publications

Display Publications by [Year] [Type] [Topic]


Combining Difference Rewards and Hierarchies for Scaling to Large Multiagent System. C. Holmes Parker and K. Tumer. In AAMAS-2012 Workshop on Adaptive and Learning Agents, Valencia, Spain, June 2012.

Abstract

Coordinating the actions of agents in multiagent systems presents a challenging problem, especially as the size of the system is increased and predicting the agent interactions becomes difficult. Many approaches to improving coordination within multiagent systems have been developed including organizational structures, shaped rewards, coordination graphs, heuristic methods, and learning automata. However, each of these approaches still have limitations with respect to scalability. The goal of this paper is to combine two such coordination mechanisms (difference rewards and hierarchical organization) to improve scalability. We combine difference rewards and hierarchical organizations in the Defect Combination Problem (DCP) with 10,000 sensing agents. We show that combining these techniques results in significantly improved performance and robustness compared to either approach individually. In particular, we show that combining hierarchical organization with difference rewards can improve both coordination and scalability by decreasing information overhead, structuring agent-to-agent connectivity and control flow, and improving the individual decision making capabilities of agents.

Download

(unavailable)

BibTeX Entry

@incollection{tumer-holmesparker_ala12,
        author = {C. Holmes Parker  and K. Tumer},
        title = {Combining Difference Rewards and Hierarchies for Scaling to Large Multiagent System},
        booktitle = {AAMAS-2012 Workshop on Adaptive and Learning Agents},
	month = {June},
	address = {Valencia, Spain},
	editors = {E. Howley and P. Vrancx and M. Knudson},
	abstract={Coordinating the actions of agents in multiagent systems presents a challenging problem, especially as the size of the system is increased and predicting the agent interactions becomes difficult. Many approaches to improving coordination within multiagent systems have been developed including organizational structures, shaped rewards, coordination graphs, heuristic methods, and learning automata. However, each of these approaches still have limitations with respect to scalability. The goal of this paper is to combine two such coordination mechanisms (difference rewards and hierarchical organization) to improve scalability. We combine difference rewards and hierarchical organizations in the Defect Combination Problem (DCP) with 10,000 sensing agents. We show that combining these techniques results in significantly improved performance and robustness compared to either approach individually. In particular, we show that combining hierarchical organization with difference rewards can improve both coordination and scalability by decreasing information overhead, structuring agent-to-agent connectivity and control flow, and improving the individual decision making capabilities of agents.},
	bib2html_pubtype = {Workshop/Symposium Papers},
	bib2html_rescat = {Multiagent Systems, Reinforcement Learning},
        year = {2012}
}

Generated by bib2html.pl (written by Patrick Riley ) on Tue Jun 26, 2018 19:10:42