Information Thermodynamics of Agents: The Work Capacity of Channels with Memory

arXiv:2504.06209v2 Announce Type: replace-cross Abstract: 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, based on the second law of thermodynamics, has even been shown to be necessary for reaching the fundamental energetic limits of information processing on a tape. 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, defined as the maximum rate at which an agent can expect to extract work from its environment. Our results reveal that work-efficient agents must balance prediction and forgetting. 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.

Abstract: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, based on the second law of thermodynamics, has even been shown to be necessary for reaching the fundamental energetic limits of information processing on a tape. 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, defined as the maximum rate at which an agent can expect to extract work from its environment. Our results reveal that work-efficient agents must balance prediction and forgetting. 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.

14+37 pages. Substantially revised version with an expanded agent-environment framework and additional examples

Machine Learning (cs.LG); Statistical Mechanics (cond-mat.stat-mech); Information Theory (cs.IT); Adaptation and Self-Organizing Systems (nlin.AO); Chaotic Dynamics (nlin.CD); Quantum Physics (quant-ph)

arXiv:2504.06209 [cs.LG]

(or arXiv:2504.06209v2 [cs.LG] for this version)

From: Lukas J. Fiderer [view email] [v1] Tue, 8 Apr 2025 16:54:20 UTC (529 KB) [v2] Wed, 30 Sep 2026 16:27:50 UTC (675 KB)

aiqbench analysis

Information Thermodynamics of Agents: The Work Capacity of Channels with Memory

Related coverage