Network-based Active Inference for Adaptive and Cost-efficient Real-World Applications: A Benchmark Study of a Valve-turning Task Against Deep Reinforcement Learning

ICLR 2025 Conference Submission12621 Authors

Keywords: Active Inference (AIF), Deep Reinforcement Learning (DRL), Free Energy Principle (FEP), Robotics, Trajectory generation, Random dynamical systems, Random attractor dynamics, Non-Equilibrium Steady State (NESS), Adaptive control, Industrial automation, Computational efficiency, Cost-efficient solutions

TL;DR: This paper introduces Network-based Active Inference (NetAIF), a game-changing framework that merges Active Inference with network dynamics, outperforming Deep Reinforcement Learning while slashing computational costs and time by orders of magnitude.

Abstract: This paper introduces Network-based Active Inference (NetAIF), a novel approach that integrates Active Inference (AIF) principles with network dynamics to enable adaptive, cost-efficient real-world applications. In benchmark tests against Deep Reinforcement Learning (DRL), NetAIF outperforms DRL in both computational efficiency and task performance. Leveraging random attractor dynamics, NetAIF generates real-time trajectories, allowing robots to adapt to complex, dynamic environments without the need for extensive pre-training. We demonstrate NetAIF's superiority in industrial valve manipulation, achieving over 99\% accuracy in goal position and orientation in untrained dynamic environments, with a 45,000-fold reduction in computational costs. NetAIF is approximately 100,000 times more efficient in iteration count than DRL, making it a highly robust and efficient solution for industrial applications.

Primary Area: probabilistic methods (Bayesian methods, variational inference, sampling, UQ, etc.)

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 12621