arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2003.12151math.OCcs.LGcs.SYeess.SY
收藏

正则化平均场对策中的Q学习

Q-Learning in Regularized Mean-field Games

Özyeğin University(奥兹耶金大学);Bilkent University(比尔肯特大学)

Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi

摘要:

在本文中,我们引入了一个正则化的平均场博弈,并研究了这个博弈在无限时域折扣报酬函数下的学习。通过在经典的平均场对策模型的一阶段报酬函数上增加一个强凹的正则化函数来引入正则化。我们建立了一个基于值迭代的学习算法,这个正则化的平均场游戏使用拟合Q-学习。正则化项通常使强化学习算法对系统组件更具鲁棒性。此外,它使我们能够建立误差分析的学习算法,而不强加限制性的凸性假设的系统组件,这是需要在没有一个正则项。

英文摘要:

In this paper, we introduce a regularized mean-field game and study learning of this game under an infinite-horizon discounted reward function. Regularization is introduced by adding a strongly concave regularization function to the one-stage reward function in the classical mean-field game model. We establish a value iteration based learning algorithm to this regularized mean-field game using fitted Q-learning. The regularization term in general makes reinforcement learning algorithm more robust to the system components. Moreover, it enables us to establish error analysis of the learning algorithm without imposing restrictive convexity assumptions on the system components, which are needed in the absence of a regularization term.

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。

↑