An Information-Theoretic Analysis of Memory Bounds in a Distributed Resource Allocation Mechanism

Multiagent distributed resource allocation requires that agents act on limited, localized information with minimum communication overhead in order to optimize the distribution of available resources. When requirements and constraints are dynamic, learning agents may be needed to allow for adaptation. One way of accomplishing learning is to observe past outcomes, using such information to improve future decisions. When limits in agents' memory or observation capabilities are assumed, one must decide on how large should the observation window be. We investigate how this decision influences both agents' and system's performance in the context of a special class of distributed resource allocation problems, namely dispersion games. We show by numerical experiments over a specific dispersion game (the Minority Game) that in such scenario an agent's performance is non-monotonically correlated with her memory size when all other agents are kept unchanged. We then provide an information-theoretic explanation for the observed behaviors, showing that a downward causation effect takes place.

[1]  Yicheng Zhang,et al.  On the minority game: Analytical and numerical studies , 1998, cond-mat/9805084.

[2]  Yi-Cheng Zhang,et al.  Emergence of cooperation and organization in an evolutionary game , 1997 .

[3]  Yi Li,et al.  The structure of adaptive competition in minority games , 1998, adap-org/9811005.

[4]  M Andrecut,et al.  Q learning in the minority game. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[5]  Yoav Shoham,et al.  Dispersion games: general definitions and some specific learning results , 2002, AAAI/IAAI.

[6]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[7]  Yi-Cheng Zhang,et al.  Minority Games , 2008, Encyclopedia of Complexity and Systems Science.

[8]  Edmund H. Durfee,et al.  Agents Learning about Agents: A Framework and Analysis , 1997 .

[9]  K. Kaski,et al.  Intelligent minority game with genetic crossover strategies , 2002, cond-mat/0209525.

[10]  Michael P. Wellman,et al.  Online learning about other agents in a dynamic multiagent system , 1998, AGENTS '98.

[11]  Luís C. Lamb,et al.  Towards understanding the role of learning models in the dynamics of the minority game , 2004, 16th IEEE International Conference on Tools with Artificial Intelligence.

[12]  U. Michigan,et al.  Evolution in minority games. (II). Games with variable strategy spaces , 1999, adap-org/9906001.

[13]  Yoav Shoham,et al.  On the Agenda(s) of Research on Multi-Agent Learning , 2004, AAAI Technical Report.

[14]  Yoav Shoham,et al.  Learning against opponents with bounded memory , 2005, IJCAI.

[15]  Michael A. Goodrich,et al.  Learning to compete, compromise, and cooperate in repeated general-sum games , 2005, ICML.

[16]  W. Arthur.  Inductive Reasoning and Bounded Rationality , 1994 .