Computing pure nash equilibria in graphical games via markov random fields

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, when combined with the junction tree algorithm for statistical inference, yields a unified proof of all previously known tractable cases of the NP-complete problem of finding pure Nash equilibria in graphical games, but also implies efficient algorithms for new classes, such as the games with O(log n) treewidth. Furthermore, this important problem becomes susceptible to a wealth of sophisticated and empirically successful techniques from Machine Learning.

Hali tarjima qilinmagan