Realizing Active Inference in Variational Message Passing: The Outcome-Blind Certainty Seeker

DOI10.1162/NECO_A_01422MaRDI QIDQ5033554zbMATHOpenAlexFDO

Authors Théophile Champion, Marek Grześ, Howard Bowman

Publication date 23 February 2022

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2104.11798

Mathematics Subject Classification ID

Cognitive psychology (91E10)

Abstract: Active inference is a state-of-the-art framework in neuroscience that offers a unified theory of brain function. It is also proposed as a framework for planning in AI. Unfortunately, the complex mathematics required to create new models -- can impede application of active inference in neuroscience and AI research. This paper addresses this problem by providing a complete mathematical treatment of the active inference framework -- in discrete time and state spaces -- and the derivation of the update equations for any new model. We leverage the theoretical connection between active inference and variational message passing as describe by John Winn and Christopher M. Bishop in 2005. Since, variational message passing is a well-defined methodology for deriving Bayesian belief update equations, this paper opens the door to advanced generative models for active inference. We show that using a fully factorized variational distribution simplifies the expected free energy -- that furnishes priors over policies -- so that agents seek unambiguous states. Finally, we consider future extensions that support deep tree searches for sequential policy optimisation -- based upon structure learning and belief propagation.

Recommendations

• Deep active inference as variational policy gradients
• Variational message passing
• Chance-Constrained Active Inference
• Deep active inference
• Active Inference: Demystified and Compared
• Active inference, belief propagation, and the Bethe approximation
• Gauging variational inference
• Probabilistic programming with stochastic variational message passing

Cited in

(8)

• A step-by-step tutorial on active inference and its application to empirical data
• Deep active inference as variational policy gradients
• Active inference on discrete state-spaces: a synthesis
• Branching time active inference with Bayesian filtering
• Predictive processing in cognitive robotics: a review
• Branching time active inference: the theory and its generality
• Active inference, belief propagation, and the Bethe approximation
• Reward Maximization Through Discrete Active Inference

This page was built for publication: Realizing Active Inference in Variational Message Passing: The Outcome-Blind Certainty Seeker

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5033554)