标题： 具有记忆的信道的工作能力：感知-行动循环中的最大可提取功 显示英文标题

标题： The Work Capacity of Channels with Memory: Maximum Extractable Work in Percept-Action Loops

摘要： 预测未来观测值在机器学习、生物学、经济学以及许多其他领域中起着核心作用。 它位于变分自由能原理等组织原则的核心，并且已经通过热力学第二定律证明——为了达到顺序信息处理的基本能量限制，这是必要的。 尽管预测范式的有用性毋庸置疑，但与环境相互作用的复杂自适应系统不仅仅是预测机器：它们有能力对其环境采取行动并引发变化。 在这项工作中，我们开发了一个框架来分析感知-行动回路中信息处理的热力学——这是一种代理-环境交互模型——使我们能够以平等的方式研究行动和感知的热力学影响。 为此，我们引入了功容量的概念——代理可以预期从环境中提取功的最大速率。 我们的结果揭示，在行为具有可观察后果的环境中，两种先前确立的工作高效代理的设计原则——最大化预测能力和遗忘过去行为——均不再是最优选择。 相反，出现了一种权衡：工作高效的代理必须平衡预测和遗忘，因为记住过去的行为可能会减少可用的自由能。 这突显了被动观察热力学的根本偏离，表明在主动学习系统中，预测和能量效率可能是对立的。 显示英文摘要

摘要： Predicting future observations plays a central role in machine learning, biology, economics, and many other fields. It lies at the heart of organizational principles such as the variational free energy principle and has even been shown -- based on the second law of thermodynamics -- to be necessary for reaching the fundamental energetic limits of sequential information processing. While the usefulness of the predictive paradigm is undisputed, complex adaptive systems that interact with their environment are more than just predictive machines: they have the power to act upon their environment and cause change. In this work, we develop a framework to analyze the thermodynamics of information processing in percept-action loops -- a model of agent-environment interaction -- allowing us to investigate the thermodynamic implications of actions and percepts on equal footing. To this end, we introduce the concept of work capacity -- the maximum rate at which an agent can expect to extract work from its environment. Our results reveal that neither of two previously established design principles for work-efficient agents -- maximizing predictive power and forgetting past actions -- remains optimal in environments where actions have observable consequences. Instead, a trade-off emerges: work-efficient agents must balance prediction and forgetting, as remembering past actions can reduce the available free energy. This highlights a fundamental departure from the thermodynamics of passive observation, suggesting that prediction and energy efficiency may be at odds in active learning systems.