Active Inference, Belief Propagation, and the Bethe Approximation

DOI10.1162/neco_a_01108zbMath1471.91411OpenAlexW2811289501WikidataQ89289959 ScholiaQ89289959MaRDI QIDQ5157239

Sarah Schwöbel, Stefan J. Kiebel, Dimitrije Marković

Publication date: 12 October 2021

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/neco_a_01108

Mathematics Subject Classification ID

Cognitive psychology (91E10)

Related Items (6)

Active inference on discrete state-spaces: a synthesis ⋮ Bayesian Brains and the Rényi Divergence ⋮ Retrospective surprise: a computational component for active inference ⋮ Balancing control: a Bayesian interpretation of habitual and goal-directed behavior ⋮ Whence the Expected Free Energy? ⋮ Enhanced Equivalence Projective Simulation: A Framework for Modeling Formation of Stimulus Equivalence Classes

Uses Software

• PMTK
• Omniglot
• PRMLT

Cites Work

• Planning and navigation as active inference
• Optimal control of Markov processes with incomplete state information
• Human-level concept learning through probabilistic program induction
• Belief Propagation in Networks of Spiking Neurons
• Constructing Free-Energy Approximations and Generalized Belief Propagation Algorithms
• Graphical Models, Exponential Families, and Variational Inference
• State of the Art—A Survey of Partially Observable Markov Decision Processes: Theory, Models, and Algorithms
• Active Inference: A Process Theory
• Statistical theory of superlattices
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Active Inference, Belief Propagation, and the Bethe Approximation