• Corpus ID: 246275627

Public Information Representation for Adversarial Team Games

  title={Public Information Representation for Adversarial Team Games},
  author={Luca Carminati and Federico Cacciamani and Marco Ciccone and Nicola Gatti},
The study of sequential games in which a team plays against an adversary is receiving an increasing attention in the scientific literature. Their peculiarity resides in the asymmetric information available to the team members during the play which makes the equilibrium computation problem hard even with zero-sum payoffs. The algorithms available in the literature work with implicit representations of the strategy space and mainly resort to Linear Programming and column generation techniques… 

Team Belief DAG Form: A Concise Representation for Team-Correlated Game-Theoretic Decision Making

A new representation for team-coordinated game-theoretic decision making, which is coined the team belief DAG (TB-DAG) , which can be exponentially tighter than that of Zhang and Sandholm [19] in some cases.

A Survey of Decision Making in Adversarial Games

This paper provides a systematic survey on three main game models widely employed in adversarial games, i.e., zero-sum normal-form and extensive-form games, Stackelberg (security) games, zero- sum differential games, from an array of perspectives, including basic knowledge of game models, (approximate) equilibrium concepts, problem classifications, research frontiers, (assumed) optimal strategy seeking techniques, prevailing algorithms, and practical applications.

For Learning in Symmetric Teams, Local Optima are Global Nash Equilibria

Although it has been known since the 1970s that a globally optimal strategy profile in a common-payoff game is a Nash equilibrium, global optimality is a strict requirement that limits the re-sult’s


The size of the representation scales with the amount of information uncommon to the team, and using linear programming on top of the team belief DAG form to solve for a team correlated equilibrium in an adversarial team games recovers almost exactly their algorithm.

Abstracting Imperfect Information Away from Two-Player Zero-Sum Games

ING IMPERFECT INFORMATION AWAY FROM TWO-PLAYER ZERO-SUM GAMES Samuel Sokota Carnegie Mellon University ssokota@andrew.cmu.edu Ryan D’Orazio Mila, Université de Montréal ryan.dorazio@mila.quebec Chun



Computational Results for Extensive-Form Adversarial Team Games

This work provides the first computational study of extensive-form adversarial team games, sequential, zero-sum games in which a team of players, sharing the same utility function, faces an adversary.

Coordination in Adversarial Sequential Team Games via Multi-Agent Deep Reinforcement Learning

Soft Team Actor-Critic (STAC) is introduced as a solution to the team's coordination problem that does not require any prior domain knowledge and reaches near-optimal coordinated strategies both in perfectly observable and partially observable games, where previous deep RL algorithms fail to reach optimal coordinated behaviors.

Multi-Agent Coordination in Adversarial Environments through Signal Mediated Strategies

This work introduces a signaling-based framework to represent team coordinated strategies given a buffer of past experiences and empirically shows convergence to coordinated equilibria in cases where previous state-of-the-art multi-agent RL algorithms did not.

Ex ante coordination and collusion in zero-sum multi-player extensive-form games

A sound way is provided to map the problem of finding an optimal ex-ante-correlated strategy for the team to the well-understood Nash equilibrium-finding problem in a (larger) two-player zero-sum perfect-recall game and proposes a new game representation, the realization form, that generalizes the sequence form but can also be applied to imperfect-Recall games.

Computing the Team-maxmin Equilibrium in Single-Team Single-Adversary Team Games

The Team–maxmin equilibrium is investigated, characterizing the utility of the team and showing that it can be irrational, and two approximation algorithms are proposed, which are a modified version of an already existing algorithm and a novel anytime algorithm.

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

This paper provides new modeling results about computing such an optimal distribution for a team of players that faces an opponent in an imperfect-information zero-sum extensive-form game and develops an efficient column-generation algorithm that allows one for capping the number of profiles employed in the solution.

Team-Maxmin Equilibrium: Efficiency Bounds and Algorithms

Borders of (in)efficiency of the Team-maxmin equilibrium w.r.t. the NashEquilibrium when the team members can play correlated strategies are investigated, as well as a number of algorithms to find and/or approximate an equilibrium.

Team-Maxmin Equilibria☆

Abstract In a noncooperative game, a team is a set of players that have identical payoffs. We investigate zero-sum games where a team of several players plays against a single adversary. The team is

Solving Common-Payoff Games with Approximate Policy Iteration

This work proposes CAPI, a novel algorithm which, like BAD, combines common knowledge with deep reinforcement learning, however, unlike BAD, CAPI prioritizes the propensity to discover optimal joint policies over scalability.

Deep Counterfactual Regret Minimization

Deep Counterfactual Regret Minimization is introduced, a form of CFR that obviates the need for abstraction by instead using deep neural networks to approximate the behavior of CFR in the full game.