Q-Tree Search: An Information-Theoretic Approach Toward Hierarchical Abstractions for Agents With Computational Limitations
Q-Tree Search: An Information-Theoretic Approach Toward Hierarchical Abstractions for Agents With Computational Limitations
复制标题
DOI：
10.1109/tro.2020.3003219
复制
发表时间：
2020-12-01
影响因子：
7.8
通讯作者：
Tsiotras, Panagiotis
中科院分区：
文献类型：
--
作者：
Larsson, Daniel T.;Maity, Dipankar;Tsiotras, Panagiotis
在本文中，我们开发了一个框架来获得用于决策的图抽象，其中抽象作为代理的可用资源的函数出现。我们讨论了提出的方法与信息论信号压缩的联系，并提出了一个新的优化问题来获得基于树的抽象，该抽象是代理计算资源的函数。文中详细讨论了新问题的结构性质，并提出了两种算法。我们讨论了这两个算法得到的解的质量，并证明了它们之间的关系。该框架被应用于各种环境，以获得分层抽象。
In this article, we develop a framework to obtain graph abstractions for decision-making where the abstractions emerge as a function of the agent's available resources. We discuss the connection of the proposed approach with information-theoretic signal compression and formulate a novel optimization problem to obtain tree-based abstractions that are a function of the agent's computational resources. The structural properties of the new problem are discussed in detail and two algorithmic approaches are proposed. We discuss the quality of, and prove relationships between, the solutions obtained by the two proposed algorithms. The framework is applied to a variety of environments to obtain hierarchical abstractions.