arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1603.09173math.OCcs.GTmath.DS
收藏

黎曼博弈动力学

Riemannian game dynamics

Panayotis Mertikopoulos, WIlliam H. Sandholm

摘要:

我们研究了一类进化博弈动态平衡的收益所确定的游戏的回报对运动的成本,捕捉的困难,人口之间的状态移动。运动的成本由黎曼度量表示,即,人口状态集合的状态依赖内积。复制动力学和(欧几里德)投影动力学是我们研究的类的原型例子。像这些代表性的动力学,所有黎曼博弈动力学满足某些基本的必要条件,包括正相关和整体收敛潜在的游戏。此外,当基本的黎曼度量满足海森可积条件时,所得到的动力学保持了复制子和投影动力学的许多进一步的性质。我们研究了Hessian博弈动力学和正规形式博弈中的强化学习之间的密切联系,扩展并阐明了复制动力学和指数强化学习之间的一个众所周知的联系。

英文摘要:

We study a class of evolutionary game dynamics defined by balancing a gain determined by the game's payoffs against a cost of motion that captures the difficulty with which the population moves between states. Costs of motion are represented by a Riemannian metric, i.e., a state-dependent inner product on the set of population states. The replicator dynamics and the (Euclidean) projection dynamics are the archetypal examples of the class we study. Like these representative dynamics, all Riemannian game dynamics satisfy certain basic desiderata, including positive correlation and global convergence in potential games. Moreover, when the underlying Riemannian metric satisfies a Hessian integrability condition, the resulting dynamics preserve many further properties of the replicator and projection dynamics. We examine the close connections between Hessian game dynamics and reinforcement learning in normal form games, extending and elucidating a well-known link between the replicator dynamics and exponential reinforcement learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑