The Team-maxmin equilibrium prescribes the optimal strategies for a team of rational players sharing the same goal and without the capability of correlating their strategies in strategic games against an adversary. This solution concept can capture situations in which an agent controls multiple resources-corresponding to the team members-that cannot communicate. It is known that such equilibrium always exists and it is unique (unless degeneracy) and these properties make it a credible solution concept to be used in real-world applications, especially in security scenarios. Nevertheless, to the best of our knowledge, the Team-maxmin equilibrium is almost completely unexplored in the literature. In this paper, we investigate bounds of (in)efficiency of the Team-maxmin equilibrium w.r.t. the Nash equilibria and w.r.t. the Maxmin equilibrium when the team members can play correlated strategies. Furthermore, we study a number of algorithms to find and/or approximate an equilibrium, discussing their theoretical guarantees and evaluating their performance by using a standard testbed of game instances.
Computing Ex Ante Equilibrium in Heterogeneous Zero-Sum Team Games
Shanghai Jiao Tong University(上海交通大学);Peking University(北京大学);Nanyang Technological University(南洋理工大学);CAIR, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences(中国科学院香港创新研究院 CAIR)
针对异构零和团队博弈中 Team PSRO 策略表达不足的问题,提出带顺序关联机制的 H-PSRO,保证奖励单调改善并降低可利用性,实验验证其收敛性与优势。
Independent RL for Cooperative-Competitive Agents: A Mean-Field Perspective
Analog Devices Incorporated(亚德诺半导体公司);Artificial Intelligence Research, JP Morgan Chase & Co(摩根大通公司人工智能研究部门);School of Mathematics and Data Science, NYU Shanghai(上海纽约大学数学与数据科学学院);Coordinated Science Lab, University of Illinois, Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校协调科学实验室)
分散在线规划可以是一个有吸引力的合作多智能体系统的范例,由于改进的可扩展性和鲁棒性。这种方法的一个关键困难在于对其他代理人的决策做出准确的预测。在本文中,我们提出了一个可训练的在线分散规划算法的基础上分散的蒙特卡罗树搜索,结合模型的队友从以前的情节运行。通过只允许一个代理,以适应其模型在一个时间,在理想的政策近似的假设下,我们的方法的连续迭代保证改善联合政策,并最终导致收敛到一个纳什均衡。我们通过在[Claes et al.,2015年]。我们表明,深度学习和卷积神经网络可以用来产生精确的策略近似器,利用问题的空间特征,并且所提出的算法提高了基线规划性能,特别是具有挑战性的域配置。