arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.10014econ.THcs.LGq-fin.CP
收藏

强化学习在经济和金融中的应用

Reinforcement Learning in Economics and Finance

Université du Québec à Montréal (UQAM)(蒙特利尔魁北克大学);Université Gustave Eiffel(古斯塔夫·埃菲尔大学);CNRS(法国国家科学研究中心)

Arthur Charpentier, Romuald Elie, Carl Remlinger

摘要:

强化学习算法描述了智能体如何通过重复的经验在顺序决策过程中学习最优的行动策略。在给定的环境中,代理策略为他提供了一些运行和终端奖励。与在线学习一样,智能体也是顺序学习的。在多臂强盗问题中,当一个代理人选择一个行动时,他不能事后推断其他行动选择引起的奖励。在强化学习中,他的行为会产生后果:它们不仅会影响奖励,还会影响世界的未来状态。强化学习的目标是找到一个最优策略--一个从世界状态到行动集合的映射,以最大化累积奖励,这是一个长期策略。探索可能在短期内是次优的,但可能导致最佳的长期目标。许多在经济学中流行了四十多年的最优控制问题可以在强化学习框架中表达,而计算科学的最新进展,特别是深度学习算法,可以被经济学家用来解决复杂的行为问题。在这篇文章中,我们提出了一个国家的最先进的强化学习技术,并在经济学,博弈论,运筹学和金融目前的应用。

英文摘要:

Reinforcement learning algorithms describe how an agent can learn an optimal action policy in a sequential decision process, through repeated experience. In a given environment, the agent policy provides him some running and terminal rewards. As in online learning, the agent learns sequentially. As in multi-armed bandit problems, when an agent picks an action, he can not infer ex-post the rewards induced by other action choices. In reinforcement learning, his actions have consequences: they influence not only rewards, but also future states of the world. The goal of reinforcement learning is to find an optimal policy -- a mapping from the states of the world to the set of actions, in order to maximize cumulative reward, which is a long term strategy. Exploring might be sub-optimal on a short-term horizon but could lead to optimal long-term ones. Many problems of optimal control, popular in economics for more than forty years, can be expressed in the reinforcement learning framework, and recent advances in computational science, provided in particular by deep learning algorithms, can be used by economists in order to solve complex behavioral problems. In this article, we propose a state-of-the-art of reinforcement learning techniques, and present applications in economics, game theory, operation research and finance.

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。

↑