[2508.02197] A Message Passing Realization of Expected Free Energy Minimization

Computer Science > Artificial Intelligence arXiv:2508.02197 (cs) [Submitted on 4 Aug 2025 (v1), last revised 2 Mar 2026 (this version, v3)] Title:A Message Passing Realization of Expected Free Energy Minimization Authors:Wouter W. L. Nuijten, Mykola Lukashchuk, Thijs van de Laar, Bert de Vries View a PDF of the paper titled A Message Passing Realization of Expected Free Energy Minimization, by Wouter W. L. Nuijten and 3 other authors View PDF Abstract:We present a message passing approach to Expected Free Energy (EFE) minimization on factor graphs, based on the theory introduced in arXiv:2504.14898. By reformulating EFE minimization as Variational Free Energy minimization with epistemic priors, we transform a combinatorial search problem into a tractable inference problem solvable through standard variational techniques. Applying our message passing method to factorized state-space models enables efficient policy inference. We evaluate our method on environments with epistemic uncertainty: a stochastic gridworld and a partially observable Minigrid task. Agents using our approach consistently outperform conventional KL-control agents on these tasks, showing more robust planning and efficient exploration under uncertainty. In the stochastic gridworld environment, EFE-minimizing agents avoid risky paths, while in the partially observable minigrid setting, they conduct more systematic information-seeking. This approach bridges active inference theory with practical implementat...