A Minimal Active Inference Agent

TL;DR

This paper introduces a simple active inference agent model that predicts its position in a discretized world, illustrating core ideas of the free-energy principle in an accessible way.

Contribution

It presents a minimal, agent-based model demonstrating active inference and free-energy concepts in a straightforward, understandable manner for diverse scientific audiences.

Findings

The agent successfully predicts its position using active inference.

The model illustrates how free-energy minimization guides agent behavior.

It provides an accessible example of complex theoretical ideas.

Abstract

Research on the so-called "free-energy principle'' (FEP) in cognitive neuroscience is becoming increasingly high-profile. To date, introductions to this theory have proved difficult for many readers to follow, but it depends mainly upon two relatively simple ideas: firstly that normative or teleological values can be expressed as probability distributions (active inference), and secondly that approximate Bayesian reasoning can be effectively performed by gradient descent on model parameters (the free-energy principle). The notion of active inference is of great interest for a number of disciplines including cognitive science and artificial intelligence, as well as cognitive neuroscience, and deserves to be more widely known. This paper attempts to provide an accessible introduction to active inference and informational free-energy, for readers from a range of scientific backgrounds. In this work introduce an agent-based model with an agent trying to make predictions about its position in a one-dimensional discretized world using methods from the FEP.