Extending the Entropic Potential of Events for Uncertainty Quantification and Decision-Making in Artificial Intelligence
This work addresses uncertainty modeling for AI systems, offering a theoretically grounded and interpretable framework, but it appears incremental as it builds on existing physics concepts without demonstrating broad SOTA gains.
The paper tackles the problem of uncertainty quantification and decision-making in AI by adapting the concept of entropic potential from physics to measure how discrete events influence future uncertainty, with applications in policy evaluation, reward design, explainable AI, and anomaly detection.
This work demonstrates how the concept of the entropic potential of events -- a parameter quantifying the influence of discrete events on the expected future entropy of a system -- can enhance uncertainty quantification, decision-making, and interpretability in artificial intelligence (AI). Building on its original formulation in physics, the framework is adapted for AI by introducing an event-centric measure that captures how actions, observations, or other discrete occurrences impact uncertainty at future time horizons. Both the original and AI-adjusted definitions of entropic potential are formalized, with the latter emphasizing conditional expectations to account for counterfactual scenarios. Applications are explored in policy evaluation, intrinsic reward design, explainable AI, and anomaly detection, highlighting the metric's potential to unify and strengthen uncertainty modeling in intelligent systems. Conceptual examples illustrate its use in reinforcement learning, Bayesian inference, and anomaly detection, while practical considerations for computation in complex AI models are discussed. The entropic potential framework offers a theoretically grounded, interpretable, and versatile approach to managing uncertainty in AI, bridging principles from thermodynamics, information theory, and machine learning.