Active inference on discrete state-spaces: a synthesis

Abstract

Active inference is a normative principle underwriting perception, action, planning, decision-making and learning in biological or artificial agents. From its inception, its associated process theory has grown to incorporate complex generative models, enabling simulation of a wide range of complex behaviours. Due to successive developments in active inference, it is often difficult to see how its underlying principle relates to process theories and practical implementation. In this paper, we try to bridge this gap by providing a complete mathematical synthesis of active inference on discrete state-space models. This technical summary provides an overview of the theory, derives neuronal dynamics from first principles and relates this dynamics to biological processes. Furthermore, this paper provides a fundamental building block needed to understand active inference for mixed generative models; allowing continuous sensations to inform discrete representations. This paper may be used as follows: to guide research towards outstanding challenges, a practical guide on how to implement active inference to simulate experimental behaviour, or a pointer towards various in-silico neurophysiological responses that may be used to make empirical predictions.

36 pages, 5 figures

References in corpus (2)

• Variational Inference: A Review for Statisticians
• Approximate Bayesian inference as a gauge theory

Cited by in corpus (22)

• The free energy principle made simpler but not too simple
• Collective behavior from surprise minimization
• Some interesting observations on the free energy principle
• An empirical evaluation of active inference in multi-armed bandits
• The Free Energy Principle for Perception and Action: A Deep Learning Perspective
• Designing Ecosystems of Intelligence from First Principles
• Neural dynamics under active inference: plausibility and efficiency of information processing
• Modeling motor control in continuous-time Active Inference: a survey
• On efficient computation in active inference
• Active Inference and Epistemic Value in Graphical Models
• Bayesian mechanics of perceptual inference and motor control in the brain
• How particular is the physics of the free energy principle?
• Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents
• Active Inference for Stochastic Control
• AIDA: An Active Inference-based Design Agent for Audio Processing Algorithms
• On Predictive planning and counterfactual learning in active inference
• A Bayesian perspective on classical control
• A Concise Mathematical Description of Active Inference in Discrete Time
• pymdp: A Python library for active inference in discrete state spaces
• Quantifying imperfect cognition via achieved information gain
• Grid-SD2E: A General Grid-Feedback in a System for Cognitive Learning
• Influence of the Geometry of the world model on Curiosity Based Exploration