Simulating Biological Intelligence: Active Inference with Experiment-Informed Generative Model

TL;DR

This paper introduces a biologically inspired active inference framework for modeling decision-making in autonomous agents, using experiment-informed generative models to simulate learning and planning, advancing explainable AI.

Contribution

It presents a novel active inference approach with experiment-informed generative models for decision-making in embodied agents, bridging biological plausibility and AI.

Findings

Agents demonstrate learning capabilities in simulated environments.

Memory-based learning and predictive planning are key to decision-making.

The approach offers insights into biologically plausible AI systems.

Abstract

With recent and rapid advancements in artificial intelligence (AI), understanding the foundation of purposeful behaviour in autonomous agents is crucial for developing safe and efficient systems. While artificial neural networks have dominated the path to AI, recent studies are exploring the potential of biologically based systems, such as networks of living biological neuronal networks. Along with promises of high power and data efficiency, these systems may also inform more explainable and biologically plausible models. In this work, we propose a framework rooted in active inference, a general theory of behaviour, to model decision-making in embodied agents. Using experiment-informed generative models, we simulate decision-making processes in a simulated game-play environment, mirroring experimental setups that use biological neurons. Our results demonstrate learning in these agents, providing insights into the role of memory-based learning and predictive planning in intelligent decision-making. This work contributes to the growing field of explainable AI by offering a biologically grounded and scalable approach to understanding purposeful behaviour in agents.