Dispersion games: general definitions and some specific learning results

Authors:
Trond Grenager;Rob Powers;Yoav Shoham
Affiliations:
Computer Science Department, Stanford University, Stanford, CA;Computer Science Department, Stanford University, Stanford, CA;Computer Science Department, Stanford University, Stanford, CA
Venue:
Eighteenth national conference on Artificial intelligence
Year:
2002

Citing 5
Cited 13

The dynamics of reinforcement learning in cooperative multiagent systems

AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
Balanced Allocations

SIAM Journal on Computing
A near-optimal polynomial time algorithm for learning in certain classes of stochastic games

Artificial Intelligence
Behavioral diversity in learning robot teams

Behavioral diversity in learning robot teams
Reinforcement learning: a survey

Journal of Artificial Intelligence Research

Fast convergence of selfish rerouting

SODA '05 Proceedings of the sixteenth annual ACM-SIAM symposium on Discrete algorithms
An Evolutionary Dynamical Analysis of Multi-Agent Learning in Iterated Games

Autonomous Agents and Multi-Agent Systems
An overlay smart spaces system for load balancing in wireless LANs

Mobile Networks and Applications
On the use of memory and resources in minority games

ACM Transactions on Autonomous and Adaptive Systems (TAAS)
Exploiting user location for load balancing WLANs and improving wireless QoS

ACM Transactions on Autonomous and Adaptive Systems (TAAS)
Autonomous mobile agent routing for efficient server resource allocation

Journal of Systems and Software
An information-theoretic analysis of memory bounds in a distributed resource allocation mechanism

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Distributed QoS-sensitive band selection strategies for dynamic spectrum access in unlicensed CDMA networks

Computer Networks: The International Journal of Computer and Telecommunications Networking
Reaching correlated equilibria through multi-agent learning

The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 2
Multi-agent relational reinforcement learning

LAMAS'05 Proceedings of the First international conference on Learning and Adaption in Multi-Agent Systems
Analyzing multi-agent systems with probabilistic model checking approach

Proceedings of the 34th International Conference on Software Engineering
Software diversity: security, entropy and game theory

HotSec'12 Proceedings of the 7th USENIX conference on Hot Topics in Security
Decentralized anti-coordination through multi-agent learning

Journal of Artificial Intelligence Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

Dispersion games are the generalization of the anticoordination game to arbitrary numbers of agents and actions. In these games agents prefer outcomes in which the agents are maximally dispersed over the set of possible actions. This class of games models a large number of natural problems, including load balancing in computer science, niche selection in economics, and division of roles within a team in robotics. Our work consists of two main contributions. First, we formally define and characterize some interesting classes of dispersion games. Second, we present several learning strategies that agents can use in these games, including traditional learning rules from game theory and artificial intelligence, as well as some special purpose strategies. We then evaluate analytically and empirically the performance of each of these strategies.