Bounded Rationality, Abstraction, and Hierarchical Decision-Making: An Information-Theoretic Optimality Principle
Bounded Rationality, Abstraction, and Hierarchical Decision-Making: An Information-Theoretic Optimality Principle
复制标题
DOI：
10.3389/frobt.2015.00027
复制
发表时间：
2015-01-01
影响因子：
3.4
通讯作者：
Braun, Daniel Alexander
中科院分区：
文献类型：
--
作者：
Genewein, Tim;Leibfried, Felix;Braun, Daniel Alexander
抽象和分层信息处理是人类和动物智力的标志，是生物系统行为无与伦比的灵活性的基础。即使计算能力越来越强，在人工系统中实现这种灵活性仍然具有挑战性。在这里，我们研究了这样一个假设：抽象和分层信息处理实际上可能是信息处理能力限制的结果。特别是，我们研究了有限理性决策的信息论框架，该框架在效用最大化与信息处理成本之间进行权衡。我们将该框架的基本原理应用于具有多个信息处理节点的感知行动系统，并得出有界最优解决方案。我们展示了抽象和决策层次结构的形成如何取决于信息处理成本。我们通过示例模拟来说明理论思想，并通过形式化数学上统一的优化原理来得出结论，该原理有可能扩展到更复杂的系统。
Abstaction and hierarchical information processing are hallmarks of human and animal intelligence underlying the unrivaled flexibility of behavior in biological systems. Achieving such flexibility in artificial systems is challenging, even with more and more computational power. Here, we investigate the hypothesis that abstraction and hierarchical information processing might in fact be the consequence of limitations in information-processing power. In particular, we study an information-theoretic framework of bounded rational decision-making that trades off utility maximization against information-processing costs. We apply the basic principle of this framework to perception-action systems with multiple information-processing nodes and derive bounded-optimal solutions. We show how the formation of abstractions and decision-making hierarchies depends on information-processing costs. We illustrate the theoretical ideas with example simulations and conclude by formalizing a mathematically unifying optimization principle that could potentially be extended to more complex systems.