Learning Nash Equilibria in Monotone Games

Learning Nash Equilibria in Monotone Games
复制标题

在单调博弈中学习纳什均衡

DOI:
--
复制
发表时间:
2019
期刊:
IEEE Conference on Decision and Control
影响因子:
--
通讯作者:
M. Kamgarpour
M. Kamgarpour
中科院分区:
--
文献类型:
--
作者:
T. Tatarenko;M. Kamgarpour

文献摘要

被引文献

相似文献

我们考虑多代理决策,每个代理的成本函数取决于所有代理的策略。我们提出了一个分布式算法来学习纳什均衡,每个代理只使用她的成本函数在每个联合播放的行动,缺乏任何信息的功能形式的她的成本或其他代理的成本或策略集的值。在过去的工作中,收敛算法需要强单调性,我们证明了算法的收敛性下,仅仅单调性假设。这显著地拓宽了算法的适用性,例如对于具有线性耦合约束的游戏。
We consider multi-agent decision making where each agent’s cost function depends on all agents’ strategies. We propose a distributed algorithm to learn a Nash equilibrium, whereby each agent uses only obtained values of her cost function at each joint played action, lacking any information of the functional form of her cost or other agents’ costs or strategy sets. In contrast to past work where convergent algorithms required strong monotonicity, we prove algorithm convergence under mere monotonicity assumption. This significantly widens algorithm’s applicability, such as to games with linear coupling constraints.