A Message Passing Realization of Expected Free Energy Minimization
This work provides a practical implementation for active inference in artificial agents, addressing planning under uncertainty, though it is incremental as it builds on existing theory.
The paper tackled the problem of efficient policy inference under epistemic uncertainty by reformulating Expected Free Energy minimization as a tractable inference problem using message passing on factor graphs, resulting in agents that consistently outperformed conventional KL-control agents in stochastic gridworld and partially observable Minigrid tasks with more robust planning and exploration.
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.