首页|Polytechnic University Milan Researcher Publishes Findings in Artificial Intelli gence (Monte-Carlo Regret Minimization for Adversarial Team Games)
Polytechnic University Milan Researcher Publishes Findings in Artificial Intelli gence (Monte-Carlo Regret Minimization for Adversarial Team Games)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on artificial intelligenc e is the subject of a new report. According to news reporting from Milano, Italy,by NewsRx journalists, research stated, "We study equilibrium approximation in extensive-form adversarial team games, in which two teams of rational players c ompete in a zero-sum interaction." Our news correspondents obtained a quote from the research from Polytechnic Univ ersity Milan: "The suitable solution concept in these settings is the Team-Maxmi n Equilibrium with Correlation (TMECor), which naturally arises when the team pl ayers play ex-ante correlated strategies. While computing such an equilibrium is APX-hard, recent techniques show that scalability beyond toy instances is possi ble. However, even compact representations of the team's strategy space, such as that exploiting Directed Acyclic Graphs (DAGs), have exponential size prohibiti ng solving large instances. In the present paper, we show that Monte Carlo sampl ing for regret minimization in adversarial team games can provide an important a dvancement. In particular, we design a DAG Monte Carlo Counterfactual Regret Min imization algorithm that performs outcome sampling with O ( d ) time complexity per iteration, where d is the depth of the DAG, and with a convergence rate boun d of O ( b kd ),where b is the branching factor and k is the maximum number of private states in each public state of the team. We empirically evaluate our al gorithms with a standard testbed of games, showing their performance when approx imating equilibria."
Polytechnic University MilanMilanoIt alyEuropeArtificial IntelligenceMachine Learning
NETL
NSTL
