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 2109.06076cs.AIcs.LO
收藏

学习在部分可观察领域中采取行动和观察

Learning to Act and Observe in Partially Observable Domains

Thomas Bolander, Nina Gierasimczuk, Andrés Occhipinti Liberman

摘要:

我们考虑一个学习代理在部分可观察的环境中,代理从来没有互动过,它学习它可以观察到什么,以及它的行动如何影响环境。代理可以通过在该领域中采取行动并观察其结果所收集的经验来了解该领域。我们提出的学习算法能够学习尽可能多的(在一个定义明确的意义上)都是关于什么是直接观察到的,什么样的行动在域中,给定的学习者的观察约束。我们区分每个算法所获得的领域知识的水平,并描述所需的观测类型,以达到it.The算法使用动态认知逻辑(DEL)来表示学习领域的信息符号。我们的工作延续了Bolander和Gierasimczuk(2015)的工作,他们开发了基于DEL的学习算法,以学习完全可观察域中的域信息。

英文摘要:

We consider a learning agent in a partially observable environment, with which the agent has never interacted before, and about which it learns both what it can observe and how its actions affect the environment. The agent can learn about this domain from experience gathered by taking actions in the domain and observing their results. We present learning algorithms capable of learning as much as possible (in a well-defined sense) both about what is directly observable and about what actions do in the domain, given the learner's observational constraints. We differentiate the level of domain knowledge attained by each algorithm, and characterize the type of observations required to reach it. The algorithms use dynamic epistemic logic (DEL) to represent the learned domain information symbolically. Our work continues that of Bolander and Gierasimczuk (2015), which developed DEL-based learning algorithms based to learn domain information in fully observable domains.

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。

↑