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 2212.03201cs.LG
收藏

逆强化学习中的误指定

Misspecification in Inverse Reinforcement Learning

Oxford University(牛津大学)

Joar Skalse, Alessandro Abate

摘要:

逆强化学习(IRL)的目的是从策略$π$推断奖励函数$R$。为此,我们需要一个$π$如何与$R$相关的模型。在目前的文献中,最常见的模型是最优性,玻尔兹曼合理性和因果熵最大化。IRL背后的主要动机之一是从人类行为中推断人类偏好。然而,人类偏好和人类行为之间的真实关系比IRL目前使用的任何模型都要复杂得多。这意味着它们被错误地指定,这引起了人们的担忧,即如果将它们应用于现实世界的数据,可能会导致不合理的推论。在本文中,我们提供了一个数学分析如何强大的不同的IRL模型是错误的规格,并准确地回答如何演示政策可能不同于每个标准模型之前,该模型导致错误的推断奖励函数$R$。我们还介绍了一个框架,推理IRL中的误指定,连同正式的工具,可以用来很容易地推导出新的IRL模型的误指定的鲁棒性。

英文摘要:

The aim of Inverse Reinforcement Learning (IRL) is to infer a reward function $R$ from a policy $π$. To do this, we need a model of how $π$ relates to $R$. In the current literature, the most common models are optimality, Boltzmann rationality, and causal entropy maximisation. One of the primary motivations behind IRL is to infer human preferences from human behaviour. However, the true relationship between human preferences and human behaviour is much more complex than any of the models currently used in IRL. This means that they are misspecified, which raises the worry that they might lead to unsound inferences if applied to real-world data. In this paper, we provide a mathematical analysis of how robust different IRL models are to misspecification, and answer precisely how the demonstrator policy may differ from each of the standard models before that model leads to faulty inferences about the reward function $R$. We also introduce a framework for reasoning about misspecification in IRL, together with formal tools that can be used to easily derive the misspecification robustness of new IRL models.

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。

↑