Providing Effective Access to Shared Resources: A COIN Approach
- 428 Downloads
Managers of systems of shared resources typically have many separate goals. Examples are efficient utilization of the resources among its users and ensuring no user’s satisfaction in the system falls below a preset minimal level. Since such goals will usually conflict with one another, either implicitly or explicitly the manager must determine the relative importance of the goals, encapsulating that into an overall utility function rating the possible behaviors of the entire system. Here we demonstrate a distributed, robust, and adaptive way to optimize that overall function. Our approach is to interpose adaptive agents between each user and the system, where each such agent is working to maximize its own private utility function. In turn, each such agent’s function should be both relatively easy for the agent to learn to optimize, and “aligned” with the overall utility function of the system manager — an overall function that is based on but in general different from the satisfaction functions of the individual users. To ensure this we enhance the COllective INtelligence (COIN) framework to incorporate user satisfaction functions in the overall utility function of the system manager and accordingly in the associated private utility functions assigned to the users’ agents. We present experimental evaluations of different COIN-based private utility functions and demonstrate that those COIN-based functions outperform some natural alternatives.
KeywordsUtility Function Multiagent System Task Type COllective INtelligence Decay Factor
Unable to display preview. Download preview PDF.
- 1.Durfee, E.H.: Scaling up coordination strategies. IEEE Computer 34, 39–46 (2001)Google Scholar
- 3.Tumer, K., Wolpert, D.H.: Collective intelligence and braess paradox. In: Proceedings of the Seventeenth National Conference on Artificial Intelligence, pp. 104–109. AAAI Press, Menlo Park (2000)Google Scholar
- 4.Wolpert, D.H., Tumer, K.: Beyond mechanism design. In: Gao, H., et al. (eds.) Proceedings of International Congress of Mathematicians, Qingdao Publishing (2002)Google Scholar
- 8.Wolpert, D.H., Kirshner, S., Merz, C.J., Tumer, K.: Adaptivity in agent-based routing for data networks. In: Proc. of the 4th International Conference on Autonomous Agents, pp. 396–403 (2000)Google Scholar
- 9.Parkes, D.C.: Iterative combinatorial auctions: Theory and practice (2001)Google Scholar
- 10.Crites, R.H., Barto, A.G.: Improving elevator performance using reinforcement learning. In: Touretzky, D.S., Mozer, M.C., Hasselmo, M.E. (eds.) Advances in Neural Information Processing Systems - 8, pp. 1017–1023. MIT Press, Cambridge (1996)Google Scholar
- 11.Kephart, J.O., Hogg, T., Hubermann, B.A.: Dynamics of computational ecosystems: Implications for DAI. In: Huhns, M.N., Gasser, L. (eds.) Distributed Artificial Intelligence, Pitman. Research Notes in Artificial Intelligence, vol. 2 (1989)Google Scholar
- 12.Rustogi, S.K., Singh, M.P.: Be patient and tolerate imprecision: How autonomous agents can coordinate effectively. In: Proceedings of the International Joint Conference on Artificial Intelligence, pp.512–517 (1999)Google Scholar
- 14.Yamaki, H., Yamauchi, Y., Ishida, T.: Implementation issues on market-based qos control. In: Proceedings of the Third International Conference on Multi-Agent Systems, pp. 357–364 (1998)Google Scholar
- 16.Glance, N.S., Hogg, T.: Dilemmas in computational societies. In: First International Conference on Multiagent Systems, pp. 117–124. AAAI Press/MIT Press, Menlo Park, CA (1995)Google Scholar