{"ID":2886797,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.02197","arxiv_id":"2508.02197","title":"A Message Passing Realization of Expected Free Energy Minimization","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 implementations, providing empirical evidence for the efficiency of epistemic priors in artificial agents.","short_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 p...","url_abs":"https://arxiv.org/abs/2508.02197","url_pdf":"https://arxiv.org/pdf/2508.02197v3","authors":"[\"Wouter W. L. Nuijten\",\"Mykola Lukashchuk\",\"Thijs van de Laar\",\"Bert de Vries\"]","published":"2025-08-04T08:48:37Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"LoRA\"]","has_code":false}