Toward Design of Synthetic Active Inference Agents by Mere Mortals
This work addresses the problem of democratizing active inference for edge applications, but it is incremental as it focuses on tool development rather than a fundamental breakthrough.
The paper tackles the challenge of implementing active inference agents on edge devices despite exponential computational demands, by proposing a software toolbox to enable non-expert engineers to develop such agents effectively.
The theoretical properties of active inference agents are impressive, but how do we realize effective agents in working hardware and software on edge devices? This is an interesting problem because the computational load for policy exploration explodes exponentially, while the computational resources are very limited for edge devices. In this paper, we discuss the necessary features for a software toolbox that supports a competent non-expert engineer to develop working active inference agents. We introduce a toolbox-in-progress that aims to accelerate the democratization of active inference agents in a similar way as TensorFlow propelled applications of deep learning technology.