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 2302.14176cs.AIcs.CEmath.OC
收藏

资产减值的强化学习

Reinforcement Learning with Depreciating Assets

University of Colorado Boulder(科罗拉多大学博尔德分校)

Taylor Dohmen, Ashutosh Trivedi

摘要:

传统强化学习的一个基本假设是,奖励的价值一旦被代理接收就不会改变。目前的工作放弃了这一假设,并考虑的情况下,奖励的价值衰减成比例的时间流逝,因为它是获得。为了强调支付时发生的拐点,我们使用资产一词来指代代理人目前拥有的奖励。采用这种语言,我们开始在无限时域定量优化的框架内的资产折旧的研究。特别是,我们提出了一个资产折旧的概念,灵感来自经典的指数贴现,其中资产的价值是由固定的折扣因子在每个时间步后,它是由代理商获得缩放。在这种情况下,我们制定了贝尔曼式的最优性方程的特征,并开发了一个无模型强化学习的方法来获得最优的政策。

英文摘要:

A basic assumption of traditional reinforcement learning is that the value of a reward does not change once it is received by an agent. The present work forgoes this assumption and considers the situation where the value of a reward decays proportionally to the time elapsed since it was obtained. Emphasizing the inflection point occurring at the time of payment, we use the term asset to refer to a reward that is currently in the possession of an agent. Adopting this language, we initiate the study of depreciating assets within the framework of infinite-horizon quantitative optimization. In particular, we propose a notion of asset depreciation, inspired by classical exponential discounting, where the value of an asset is scaled by a fixed discount factor at each time step after it is obtained by the agent. We formulate a Bellman-style equational characterization of optimality in this context and develop a model-free reinforcement learning approach to obtain optimal policies.

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。

↑