paper:doi-10-1162-neco-a-01108Active Inference, Belief Propagation, and the Bethe Approximation
Original abstract (expand)
When modeling goal-directed behavior in the presence of various sources of uncertainty, planning can be described as an inference process. A solution to the problem of planning as inference was previously proposed in the active inference framework in the form of an approximate inference scheme based on variational free energy. However, this approximate scheme was based on the mean-field approximation, which assumes statistical independence of hidden variables and is known to show overconfidence and may converge to local minima of the free energy. To better capture the spatiotemporal properties of an environment, we reformulated the approximate inference process using the so-called Bethe approximation. Importantly, the Bethe approximation allows for representation of pairwise statistical dependencies. Under these assumptions, the minimizer of the variational free energy corresponds to the belief propagation algorithm, commonly used in machine learning. To illustrate the differences between the mean-field approximation and the Bethe approximation, we have simulated agent behavior in a simple goal-reaching task with different types of uncertainties. Overall, the Bethe agent achieves higher success rates in reaching goal states. We relate the better performance of the Bethe agent to more accurate predictions about the consequences of its own actions. Consequently, active inference based on the Bethe approximation extends the application range of active inference to more complex behavioral tasks.
Related work— refs + corpus + external arXiv
Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.
- ≈ 80%
- Realising Active Inference in Variational Message Passing: the Outcome-blind Certainty SeekerMarek Grze\'s, Howard Bowman Th\'eophile Champion2021≈ 79%
- Learning Perception and Planning with Deep Active InferenceTim Verbelen, Johannes Nauta, Cedric De Boom and Bart Dhoedt Ozan \c{C}atal2020≈ 78%
- ≈ 78%
- Active Inference and Human--Computer InteractionJohn H. Williamson, Sebastian Stein Roderick Murray-Smith2024≈ 78%
- Interpreting Dynamical Systems as Bayesian ReasonersNathaniel Virgo and Martin Biehl and Simon McGregor2021≈ 78%
- Active inference for action-unaware agentsKeisuke Suzuki, Ryota Kanai, Manuel Baltieri Filippo Torresan2025≈ 78%
- Active inference and artificial reasoningLancelot Da Costa, Alexander Tschantz, Conor Heins, Christopher Buckley, Tim Verbelen, Thomas Parr Karl Friston2025≈ 78%
- ≈ 78%
- Demonstrating the Continual Learning Capabilities and Practical Application of Discrete-Time Active InferenceRithvik Prakki2024≈ 78%
- Active inference: demystified and comparedPhilip J. Ball, Thomas Parr, Karl J. Friston Noor Sajid2021≈ 77%
- Active inference on discrete state-spaces: a synthesisThomas Parr, Noor Sajid, Sebastijan Veselic, Victorita Neacsu, Karl Friston Lancelot Da Costa2021≈ 77%
- ≈ 77%
- Active Inference in Robotics and Artificial Agents: Survey and ChallengesCristian Meo, Corrado Pezzato, Ajith Anil Meera, Mohamed Baioumy, Wataru Ohata, Alexander Tschantz, Beren Millidge, Martijn Wisse, Christopher L. Buckley, Jun Tani Pablo Lanillos2021≈ 77%
- Active Inference in String Diagrams: A Categorical Account of Predictive Processing and Free EnergyJohannes Kleiner, Toby St Clere Smithe Sean Tull2023≈ 77%
- ≈ 76%
- Active inference: demystified and comparedin corpus2021≈ 75%
- ≈ 74%
- Active Inference: A Process Theoryin corpus2017≈ 73%
- Active Inference, Curiosity and Insightin corpus2017≈ 71%
- ≈ 69%
- ≈ 68%
- ≈ 68%
- ≈ 67%
- Information, Processes and Gamesin corpus≈ 67%
- Interpreting Language Model Parametersin corpus2026≈ 67%
- When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Modelsin corpus2025≈ 67%
- ≈ 67%
- ≈ 67%
- ≈ 67%
Similar preprints — Semantic Scholar
Cited by (1)
- Active inference on discrete state-spaces: a synthesis
Active inference on discrete state-spaces, formalized as partially observable Markov decision processes (POMDPs) with likelihood matrix A, transition matrix B, and prior D, unifies perception, plannin