\input zb-basic
\input zb-ioport
\iteman{io-port 05473349}
\itemau{Brafman, Ronen I.; Tennenholtz, Moshe}
\itemti{On partially controlled multi-agent systems.}
\itemso{J. Artif. Intell. Res. (JAIR) 4, 477-507 (1996).}
\itemab
Summary: Motivated by the control theoretic distinction between ${\it $controllable} and ${\it $uncontrollable} events, we distinguish between two types of agents within a multi-agent system: ${\it $controllable agents}, which are directly controlled by the system's designer, and ${\it $uncontrollable agents}, which are not under the designer's direct control. We refer to such systems as ${\it $partially controlled multi-agent systems}, and we investigate how one might influence the behavior of the uncontrolled agents through appropriate design of the controlled agents. In particular, we wish to understand which problems are naturally described in these terms, what methods can be applied to influence the uncontrollable agents, the effectiveness of such methods, and whether similar methods work across different domains. Using a game-theoretic framework, the paper studies the design of partially controlled multi-agent systems in two contexts: in one context, the uncontrollable agents are expected utility maximizers, while in the other they are reinforcement learners. We suggest different techniques for controlling agents' behavior in each domain, assess their success, and examine their relationship.
\itemrv{~}
\itemcc{I.2.8 I.2.6}
\itemut{multi-agent system; controllable agents; uncontrollable agents; utility maximizers; reinforcement learners; $n$-person game; discrete event systems}
\itemli{}
\end