提出代理者'可塑性'新度量，揭示其与'赋能'的镜像关系
Plasticity as the Mirror of Empowerment
- 用广义定向信息定义可塑性，统一了信息论框架
- 发现可塑性与赋能存在此消彼长的内在张力
- 为理解智能体自主性提供新理论视角，适合认知科学与AI研究者
智能体是受过往观察影响并能改变未来观察的最小实体。其中，赋能（empowerment）概念已广泛应用于人工智能与认知科学。然而，智能体如何被观察所影响这一前向能力同样基础。本文提出以可塑性（plasticity）作为通用的以智能体为中心的度量，并揭示其与赋能的根本联系。基于一系列合理要求，我们引入新的信息论量——广义定向信息（generalized directed information），严格推广了Massey（1990）提出的定向信息，同时保留其优良性质。在此定义下，可塑性可视为赋能的镜像：二者使用相同度量，仅影响方向相反。核心结果表明，智能体的可塑性与赋能之间存在张力，提示智能体设计需兼顾两者。我们探讨了这些发现的意义，强调可塑性、赋能及其关系对理解代理性的关键作用。
原文摘要 · Abstract (English)
Agents are minimally entities that are influenced by their past observations and act to influence future observations. This latter capacity is captured by empowerment, which has served as a vital framing concept across artificial intelligence and cognitive science. This former capacity, however, is equally foundational: In what ways, and to what extent, can an agent be influenced by what it observes? In this paper, we ground this concept in a universal agent-centric measure that we refer to as plasticity, and reveal a fundamental connection to empowerment. Following a set of desiderata on a suitable definition, we define plasticity using a new information-theoretic quantity we call the generalized directed information. We show that this new quantity strictly generalizes the directed information introduced by Massey (1990) while preserving all of its desirable properties. Under this definition, we find that plasticity is well thought of as the mirror of empowerment: The two concepts are defined using the same measure, with only the direction of influence reversed. Our main result establishes a tension between the plasticity and empowerment of an agent, suggesting that agent design needs to be mindful of both characteristics. We explore the implications of these findings, and suggest that plasticity, empowerment, and their relationship are essential to understanding agency
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。