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 2301.10330cs.LGcs.AI
收藏

非平稳环境下的非策略估计

Off-Policy Evaluation for Action-Dependent Non-Stationary Environments

University of Massachusetts(马萨诸塞大学);United States Military Academy(美国军事学院);Stanford University(斯坦福大学)

Yash Chandak, Shiv Shankar, Nathaniel D. Bastian, Bruno Castro da Silva, Emma Brunskil, Philip S. Thomas

摘要:

顺序决策的方法通常建立在一个基本假设上,即潜在的决策过程是静态的。这限制了这些方法的应用,因为现实世界的问题往往会受到外部因素(被动非平稳性),与系统本身的相互作用(主动非平稳性),或两者(混合非平稳性)引起的变化。在这项工作中,我们采取了第一步的基本挑战,政策和政策外的评估结构化的变化,由于主动,被动,或混合非平稳。为了实现这个目标,我们做了一个高阶平稳性假设,使得非平稳性导致随时间的变化,但变化发生的方式是固定的。我们提出,OPEN,一个算法,它使用了双重应用的反事实推理和一种新的重要性加权工具变量回归,以获得较低的偏差和较低的方差估计的结构中的政策的过去的表现的变化。最后,我们展示了如何OPEN可以用来预测未来的表现,表现出非平稳性的现实世界中的应用程序的启发几个领域的有希望的结果。

英文摘要:

Methods for sequential decision-making are often built upon a foundational assumption that the underlying decision process is stationary. This limits the application of such methods because real-world problems are often subject to changes due to external factors (passive non-stationarity), changes induced by interactions with the system itself (active non-stationarity), or both (hybrid non-stationarity). In this work, we take the first steps towards the fundamental challenge of on-policy and off-policy evaluation amidst structured changes due to active, passive, or hybrid non-stationarity. Towards this goal, we make a higher-order stationarity assumption such that non-stationarity results in changes over time, but the way changes happen is fixed. We propose, OPEN, an algorithm that uses a double application of counterfactual reasoning and a novel importance-weighted instrument-variable regression to obtain both a lower bias and a lower variance estimate of the structure in the changes of a policy's past performances. Finally, we show promising results on how OPEN can be used to predict future performances for several domains inspired by real-world applications that exhibit non-stationarity.

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。

↑