Connecting Optimal Ex-Ante Collusion in Teams to Extensive-Form Correlation: Faster Algorithms and Positive Complexity Results

Gabriele Farina, Andrea Celli, Nicola Gatti, Tuomas Sandholm

Abstract

We focus on the problem of finding an optimal strategy for a team of two players that faces an opponent in an imperfect-information zero-sum extensive-form game. Team members are not allowed to communicate during play but can coordinate before the game. In that setting, it is known that the best the team can do is sample a profile of potentially randomized strategies (one per player) from a joint (a.k.a. correlated) probability distribution at the beginning of the game. In this paper, we first provide new modeling results about computing such an optimal distribution by drawing a connection to a different literature on extensive-form correlation. Second, we provide an algorithm that computes such an optimal distribution by only using profiles where only one of the team members gets to randomize in each profile. We can also cap the number of such profiles we allow in the solution. This begets an anytime algorithm by increasing the cap. We find that often a handful of well-chosen such profiles suffices to reach optimal utility for the team. This enables team members to reach coordination through a relatively simple and understandable plan. Finally, inspired by this observation and leveraging theoretical concepts that we introduce, we develop an efficient column-generation algorithm for finding an optimal distribution for the team. We evaluate it on a suite of common benchmark games. It is three orders of magnitude faster than the prior state of the art on games that the latter can solve and it can also solve several games that were previously unsolvable.

Bibtex entry

@inproceedings{Farina21:Connecting, title={Connecting Optimal Ex-Ante Collusion in Teams to Extensive-Form Correlation: Faster Algorithms and Positive Complexity Results}, author={Farina, Gabriele and Celli, Andrea and Gatti, Nicola and Sandholm, Tuomas}, booktitle={International Conference on Machine Learning}, year={2021} }

Download

Paper PDF

Bibtex entry

@inproceedings{Farina21:Connecting, title={Connecting Optimal Ex-Ante Collusion in Teams to Extensive-Form Correlation: Faster Algorithms and Positive Complexity Results}, author={Farina, Gabriele and Celli, Andrea and Gatti, Nicola and Sandholm, Tuomas}, booktitle={International Conference on Machine Learning}, year={2021} }

Typo or question?

Get in touch!
gfarina AT mit.edu

Metadata

Venue: ICML 2021
Topic: Decision Making, Optimization, and Computational Game Theory