In large systems, it is important for agents to learn to act effectively, but sophisticated multi-agent learning algorithms generally do not scale. An alternative approach is to ...
We present a reduction from graphical games to Markov random fields so that pure Nash equilibria in the former can be found by statistical inference on the latter. Our result, wh...
Constantinos Daskalakis, Christos H. Papadimitriou
We describe algorithms for computing Nash equilibria in structured game representations, including both graphical games and multi-agent influence diagrams (MAIDs). The algorithms...
Abstract. We study a general class of non-cooperative games coming from combinatorial covering and facility location problems. A game for k players is based on an integer programmi...
We prove NP-hardness of pure Nash equilibrium for some problems of scheduling games and connection games. The technique is standard: first, we construct a gadget without the desir...