A Minimal Active Inference Agent
This work is incremental, as it focuses on explaining existing theories for readers from various scientific backgrounds, rather than advancing the field with novel findings.
The paper tackles the challenge of making the free-energy principle and active inference accessible by introducing an agent-based model in a one-dimensional discretized world to demonstrate these concepts, aiming to provide an understandable introduction without presenting new experimental results or concrete numerical outcomes.
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.