Asynchronous Learning in Decentralized Environments: A Game-Theoretic Approach

Many of the chapters in this book consider collectives that are cooperative; all agents work together to achieve a common goal—maximizing the “world utility function.” Often this is achieved by allowing agents to behave selfishly according to some “personal utility function,” although this utility function is explicitly imposed by the designer so is not truly “selfish.” In this chapter we consider the problems that arise when agents are truly selfish and their personal utility functions are intrinsic to their behavior. As designers we cannot directly alter these utility functions arbitrarily; all we can do is to adjust the ways in which the agents interact with each other and the system in order to achieve our own design goals. In game theory, this is the mechanism design problem, and the design goal is denoted the “social choice function” (SCF). 1

[1]  Eric J. Friedman,et al.  Learning and Implementation on the Internet , 1997 .

[2]  Éva Tardos,et al.  Truthful mechanisms for one-parameter agents , 2001, Proceedings 2001 IEEE International Conference on Cluster Computing.

[3]  Noam Nisan,et al.  Algorithmic Mechanism Design , 2001, Games Econ. Behav..

[4]  Scott Shenker,et al.  Learning in Network Contexts: Experimental Results from Simulations , 2001, Games Econ. Behav..

[5]  Paul R. Milgrom,et al.  Rationalizability, Learning, and Equilibrium in Games with Strategic Complementarities , 1990 .

[6]  Joan Feigenbaum,et al.  A BGP-based mechanism for lowest-cost routing , 2002, PODC '02.

[7]  George B.Richardson.  The Theory of the Market Economy. , 1995, Revue économique.

[8]  Eric J. Friedman,et al.  Strategic properties of heterogeneous serial cost sharing , 2002, Math. Soc. Sci..

[9]  Scott Shenker,et al.  Efficient Network Allocations with Selfish Users , 1990, Performance.

[10]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, CACM.

[11]  H. Stackelberg,et al.  Marktform und Gleichgewicht , 1935 .

[12]  W. Hamilton,et al.  The evolution of cooperation. , 1984, Science.

[13]  Drew Fudenberg,et al.  Game theory (3. pr.) , 1991 .

[14]  Scott Shenker,et al.  Analysis and simulation of a fair queueing algorithm , 1989, SIGCOMM 1989.

[15]  Vijay V. Vazirani,et al.  Applications of approximation algorithms to cooperative games , 2001, STOC '01.

[16]  Matthew O. Jackson,et al.  A crash course in implementation theory , 2001, Soc. Choice Welf..

[17]  Scott Shenker,et al.  Making greed work in networks: a game-theoretic analysis of switch service disciplines , 1995, TNET.

[18]  Ilya Segal,et al.  Solutions manual for Microeconomic theory : Mas-Colell, Whinston and Green , 1997 .

[19]  Eric J. Friedman,et al.  Asynchronous Learning with Limited Information: An Experimental Analysis , 2000 .

[20]  Mark Handley,et al.  Equation-based congestion control for unicast applications , 2000, SIGCOMM.

[21]  A. Mas-Colell,et al.  Microeconomic Theory , 1995 .