IWAI 2022

3rd International Workshop
on Active Inference

19th September 2022 - Grenoble

In Conjunction with ECML/PKDD 2022

The 3rd International Workshop on Active Inference wants to bring together researchers on active inference as well as related research fields in order to discuss current trends, novel results and real-world applications. We have an interest in exploring the extent to which active inference can be used in modern machine learning settings, such as in hybrid setups combining it with deep learning, as well as to unify the latest psychological and neurological insights, and to determine how it can best be used to understand action, optimization and decision making.

Active inference is a new and increasingly popular theory of behavior and learning, which was originally developed in computational neuroscience (Friston et al., 2006) and which has since been extended to a physics of sentient systems at large. The core claim of active inference is that intelligent agents entertain a generative model of their environment, and seek to minimize the uncertainty related to the causes of their sensory observations. Mathematically, this scheme is implemented as the formulation of dynamics that minimize a tractable upper bound on the surprise associated with sensory observations, known as the negative evidence lower bound (ELBO) or variational free energy. The agents do so either by updating their generative model, so that it tracks the causes of its observations and becomes better at explaining them (i.e., perception and learning), or by inferring policies that will best resolve their uncertainty (i.e. acting), for example by selecting actions that lead to a priori preferred states, or by generating less ambiguous sensory data (Friston et al., 2017).


The workshop will take place September 19th, in conjunction with ECML/PKDD 2022. Download the full schedule here.

Responsive image

DishBrain and immunoception: Active inference at a biological interface
Anjali Bhat

Accepted presentations

Disentangling Shape and Pose for Object-Centric Deep Active Inference Models
Stefano Ferraro, Toon Van de Maele, Pietro Mazzaglia, Tim Verbelen and Bart Dhoedt

Reclaiming saliency: rhythmic precision-modulated action and perception
Filip Novicky, Ajith Meera, Thomas Parr, Karl Friston, Pablo Lanillos and Noor Sajid

Preventing Deterioration of Classification Accuracy in Predictive Coding Networks
Paul Kinghorn, Beren Millidge and Christopher Buckley

Spin glass systems as collective active inference
Conor Heins, Brennan Klein, Daphne Demekas, Miguel Aguilera and Christopher Buckley

Interpreting systems as solving POMDPs: a step towards a formal understanding of agency
Martin Biehl and Nathaniel Virgo

Knitting a Markov blanket is hard when you are out-of-equilibrium: two examples in canonical nonequilibrium models
Miguel Aguilera, Ángel Poc-López, Conor Heins and Christopher L Buckley

Mapping Husserlian phenomenology onto active inference
Mahault Albarracin, Riddhi Jain Pitliya and Maxwell Ramstead

Object-based Active Inference
Ruben van Bergen and Pablo Lanillos

Accepted posters

The Role of Valence and Meta-awareness in Mirror Self-recognition Using Hierarchical Active Inference
Jonathan Bauermeister and Pablo Lanillos

World model learning from demonstrations with active inference: application to driving behavior
Ran Wei, Alfredo Garcia, Anthony McDonald, Gustav Markkula, Johan Engstrom, Isaac Supeene and Matthew O'Kelly

Active Blockference: cadCAD with Active Inference for cognitive systems modeling
Jakub Smékal, Arhan Choudhury, Amit K. Singh, Shady El Damaty and Daniel A. Friedman

Active Inference Successor Representations
Beren Millidge and Christopher Buckley

Learning Policies for Continuous Control via Transition Models
Justus Huebotter, Serge Thill, Marcel van Gerven and Pablo Lanillos

Attachment Theory in an Active Inference Framework: How Does Our Inner Model Take Shape?
Erica Santaguida and Massimo Bergamasco

Capsule Networks as Generative Models
Alex Kiefer, Beren Millidge, Alexander Tschantz and Christopher Buckley

Home run: finding your way home by imagining trajectories
Daria de Tinguy, Pietro Mazzaglia, Tim Verbelen and Bart Dhoedt

A Novel Model for Novelty: Modeling the Emergence of Innovation from Cumulative Culture.
Natalie Kastel

Active Inference and Psychology of Expectations: A study of formalizing ViolEx
Dhanaraaj Raghuveer and Dominik Endres

AIXI, FEP-AI, and integrated world models: Towards a unified understanding of intelligence and consciousness
Adam Safron

Intention Modulation for Multi-Step Tasks in Continuous Time Active Inference
Matteo Priorelli and Ivilin Peev Stoianov

Learning Generative Models for Active Inference using Tensor Networks
Samuel Wauthier, Bram Vanhecke, Tim Verbelen and Bart Dhoedt

A Worked Example of the Bayesian Mechanics of Classical Objects
Dalton A R Sakthivadivel

A message passing perspective on planning under Active Inference
Magnus T. Koudahl, Christopher L. Buckley and Bert de Vries

Efficient search of active inference policy spaces using K-means
Alex Kiefer and Mahault Albarracin

Value Cores for Inner and Outer Alignment: Simulating Personality Formation via Iterated Policy Selection and Preference Learning with Self-World Modeling Active Inference Agents
Zahra Sheikhbahaee, Adam Safron, Nick Hay, Jeff Orchard and Jesse Hoey

Deriving time-averaged active inference from control principles
Eli Sennesh, Jordan Theriault, Jan-Willem van de Meent, Lisa Barrett and Karen Quigley

Call for papers

Papers on all subjects and applications of active inference and related research areas are welcome. Topics of interest include (but are not limited to):

Important dates

Abstract Submission Deadline: June 3rd, 2022 June 10th, 2022
Paper Submission Deadline: June 10th, 2022 June 24th, 2022
Acceptance Notification: July 13th, 2022
Camera Ready Submission Deadline: September 2nd, 2022
Workshop Date: September 19th, 2022

Paper submissions

We welcome submissions of papers with up to 8 printed pages (excluding references) in LNCS format (click here for details). Submissions will be evaluated according to their originality and relevance to the workshop, and should have an abstract of 60-150 words. Contributions should be in PDF format and submitted via Easychair (click here).

In accordance with the main conference, we will apply a double-blind review process. All papers need to be anonymized in the best of efforts. It is allowed to have a (non-anonymous) online pre-print. Reviewers will be asked not to search for them.


The workshop registrations will be handled by ECML/PKDD 2022 (click here). At least one author of each accepted paper should register for the conference.


Christopher Buckley, University of Sussex, United Kingdom
Daniela Cialfi, University of Chieti-Pescara, Italy
Pablo Lanillos, Donders Institute for Brain, Cognition and Behaviour, Netherlands
Maxwell Ramstead, VERSES Inc, USA; and University College London, United Kingdom
Noor Sajid, University College London, United Kingdom
Hideaki Shimazaki, Hokkaido University, Japan
Tim Verbelen, Ghent University - imec, Belgium

Programme committee

Christopher Buckley, University of Sussex, United Kingdom
Daniela Cialfi, University of Chieti-Pescara, Italy
Lancelot Da Costa, Imperial College London, United Kingdom
Cedric De Boom, Ghent University - imec, Belgium
Karl Friston, University College London, United Kingdom
Zafeirios Fountas, Huawei Technologies
Conor Heins, Max Planck Institute of Animal Behavior, Germany
Natalie Kastel, Univeristy of Amsterdam, Netherlands
Brennan Klein, Northeastern University, USA
Pablo Lanillos, Donders Institute for Brain, Cognition and Behaviour, Netherlands
Christoph Mathys, Aarhus University, Denmark
Mark Miller, Hokkaido University, Japan
Ayca Ozcelikkale, Uppsala University, Sweden
Thomas Parr, University College London, United Kingdom
Maxwell Ramstead, VERSES Inc, USA; and University College London, United Kingdom
Noor Sajid, University College London, United Kingdom
Panos Tigas, Oxford University, United Kingdom
Hideaki Shimazaki, Hokkaido University, Japan
Kai Ueltzhöffer, Heidelberg University, Germany
Ruben van Bergen, Radboud University, Netherlands
Tim Verbelen, Ghent University - imec, Belgium
Martijn Wisse, Delft University of Technology, Netherlands

Previous editions

2020 - Ghent (virtual)
2021 - Bilbao (virtual)


Karl Friston, James Kilner, Lee Harrison. A free energy principle for the brain. Journal of Physiology-Paris, Volume 100, Issues 1–3, 2006.

Karl J. Friston, Marco Lin, Christopher D. Frith, Giovanni Pezzulo, J. Allan Hobson, and Sasha Ondobaka. Active Inference, Curiosity and Insight. Neural Computation, 29(10): 2633–2683, 2017.