IWAI 2023

4th International Workshop
on Active Inference

13-15 September 2023 in Ghent, Belgium

The 4th 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.


The workshop will take place September 13-15th. Download the full schedule here.

Responsive image

Embodied AI with the Concept of Active Inference
Tetsuya Ogata

Tetsuya Ogata is a Professor with the Faculty of Science and Engineering, at Waseda University, and a Joint-appointed Fellow with the Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology, Tokyo. He is currently a member of the director board of the Japan Deep Learning Association (JDLA) since 2017, and a director of the Institute of AI and Robotics, at Waseda University since 2020.

Responsive image

Not only intentional: an Active Inference account of Human Motor Behavior
Antonella Maselli

Antonella Maselli currently works at the Institute of Cognitive Sciences and Technology, at the Italia National Research Council of Italy (CNR). Antonella does research in multisensory perception, cognitive sciences and motor control.

Responsive image

Directions of travel in active inference
Karl Friston

Karl Friston is a British neuroscientist and theoretician at University College London. He is a key architect of the free energy principle and active inference. In October 2022, he joined VERSES Inc, a California-based cognitive computing company focusing on artificial intelligence designed using the principles of active inference, as Chief Scientist.

Responsive image

Deep active inference
Noor Sajid

Active inference is a Bayesian framework for understanding biological intelligence. The underlying theory brings together perception and action under one single imperative: minimizing free energy (Friston, 2010). I will present a neural architecture for building deep active inference agents operating in complex, continuous state-spaces using multiple forms of Monte-Carlo (MC) sampling. For this, I will introduce several techniques, novel to active inference. These include: i) selecting free-energy-optimal policies via MC tree search, ii) approximating this optimal policy distribution via a feed-forward `habitual' network, iii) predicting future parameter belief updates using MC dropouts and, finally, iv) optimizing state transition precision (a high-end form of attention). Our approach enables agents to learn environmental dynamics efficiently, while maintaining task performance. I will illustrate this in a toy environment and demonstrate that these agents can automatically create disentangled representations that are apt for modeling state transitions. In a more complex Animal-AI environment, our agents can simulate future state transitions and actions, to evince reward-directed navigation – despite temporary suspension of visual input. Our results show that deep active inference - equipped with MC methods - provides a flexible framework to develop biologically inspired intelligent agents, with applications in both machine learning and cognitive science.

Noor Sajid is a theoretical neuroscience PhD candidate at University College London with Prof. Karl Friston. Her research is aimed at understanding the algorithms of the brain – with a particular interest in mechanisms that support biological adaptation. She investigates how artificial and biological agents adapt when interacting with their environments. Noor hopes that this work will provide insight into how neural networks of the brain implement and adapt computations after perturbations. Her work is funded by the UK Medical Research Council’s AI and Neuroscience PhD award, 2021 Microsoft PhD Research fellowship and G-Research PhD award.

Responsive image

Design of Active Inference controllers for dynamic systems
Ajith Anil Meera

Have you ever wondered how the roboticists and control engineers model and control robots? Have you been working with active inference and wanted to put it into robot? In this tutorial, the participants will gain an insight into the modelling and control of dynamic systems using active inference, from a robotics perspective. At the end, the participants will learn to i) model a dynamic system, ii) transform the model to the state space form and, iii) derive the equations for the Active Inference controller. The tutorial will follow a step by step guidance in MATLAB, to control a simple dynamic system (spring mass damper system) towards a desired goal state or goal state velocity, using the Active Inference controller. After this tutorial, the participants will be able to derive the equations of motion of a dynamic system, and design an active inference controller to control it. The same methodology will be followed to demonstrate the simulation results for i) controlling a 2DOF robot arm, ii) control a group of drones to fly in formation towards the goal by avoiding obstacles – all using the active inference controller. This tutorial is not only targeted for beginners, but also for researchers with control knowledge.

Ajith Anil Meera is a post-doctoral researcher with Dr. Pablo Lanillos, working on the EU project METATOOL at Radbound University, The Netherlands, where he investigates robotic control and tool invention with Active Inference. He obtained his PhD from the Department of Cognitive Robotics, TU Delft, on the thesis, “Free Energy Principle Based Precision Modulation for Robot Attention”. His research focuses on robot cognition, path planning, estimation and control.

Accepted papers

Toward Design of Synthetic Active Inference Agents by Mere Mortals
Bert de Vries

On Embedded Normativity - An Active Inference account of agency beyond flesh
Avel Guénin Carlut, Mahault Albarracin

Designing explainable artificial intelligence with active inference: A framework for transparent introspection and decision-making
Mahault Albarracin, Ines Hipolito, Safae Essafi-Tremblay, Jason Fox, Gabriel Rene, Maxwell Ramstead, Karl Friston

Dynamical Perception-Action Loop Formation with Developmental Embodiment for Hierarchical Active Inference
Kanako Esaki, Tadayuki Matsumura, Shunsuke Minusa, Yang Shao, Chihiro Yoshimura, Hiroyuki Mizuno

Integrating cognitive map learning and active inference for planning in ambiguous environments
Toon Van de Maele, Bart Dhoedt, Tim Verbelen, Giovanni Pezzulo

Active Inference in Hebbian Learning Networks
Ali Safa, Tim Verbelen, Lars Keuninckx, Ilja Ocket, André Bourdoux, Francky Catthoor, Georges Gielen, Gert Cauwenberghs

Contextual Qualitative Deterministic Models for Self-Learning Embodied Agents
Jan Lemeire, Nick Wouters, Marco Van Cleemput

Learning One Abstract Bit at a Time Through Self-Invented Experiments Encoded as Neural Networks
Vincent Herrmann, Louis Kirsch, Jürgen Schmidhuber

Towards Metacognitive Robot Decision Making for Tool Selection
Ajith Anil Meera, Pablo Lanillos

Probabilistic Majorization of Partially Observable Markov Decision Processes
Tom Lefebvre

Efficient motor learning through action-perception cycles in deep kinematic inference
Matteo Priorelli, Ivilin Peev Stoianov

A Model of Agential Learning Using Active Inference
Riddhi Jain Pitliya, Robin A. Murphy

Understanding Tool Discovery and Tool Innovation Using Active Inference
Poppy Collis, Paul Kinghorn, Christopher Buckley

An analytical model of active inference in the Iterated Prisoner's Dilemma
Daphne Demekas, Conor Heins, Brennan Klein

Exploring Action-Centric Representations Through the Lens of Rate-Distortion Theory
Miguel De Llanza Varona, Christopher Buckley, Beren Millidge

Towards Understanding Persons and their Personalities with Cybernetic Big 5 Theory and the Free Energy Principle and Active Inference (FEP-AI) Framework
Adam Safron, Zahra Sheikhbahaee

Relative representations for cognitive graphs
Alex B Kiefer, Christopher Buckley

Accepted posters

An Actively Inferential Neuro-AI Interface
Charles Wan

Generalized Notation Notation for Active Inference Models
Jakub Smekal, Daniel Friedman

An active inference perspective for the amygdala complex
Ronald Sladky, Dominic Kargl, Wulf Haubensak, Claus Lamm

Real-World Robot Control Based on Contrastive Active Inference with Learning from Demonstration
Kentaro Fujii, Takuya Isomura, Shingo Murata

Inventory Decision by Active Inference
Wanshan Zhu

Predictive Coding Account of Bipolar Disorder
Theodoros Sechopoulos

Objects as perceptually grounded neurosymbols for reasoning and behavior
Ruben S. van Bergen, Pablo Lanillos

Active Inference in Human-Computer Interaction
Roderick Murray-Smith, Sebastian Stein, John H Williamson

Hierarchical Active Inference for Exploration and Navigation in Structured Maze Environments
Daria de Tinguy, Toon Van de Maele, Tim Verbelen, Bart Dhoedt

A model of hippocampal-prefrontal interactions to solve spatial memory-guided tasks
Toon Van de Maele, Bart Dhoedt, Tim Verbelen, Giovanni Pezzulo

Spike coding active inference
André Rodrigues Urbano, Ajith Anil Meera, Sander Wessel Keemink, Pablo Lanillos

A Neural Network Implementation for Free Energy Principle
Jingwei Liu

Synthesising Idiographic Computational Models of Human Biometric Data With Virtually Embodied Active-Inference Agents and Their Affordances When Embedded in a Computational Ecology
Casper Hesp, Richard K Ridderinkhof

An Active Inference Approach to Attachment Theory
Erica Santaguida, Giuseppe Pagnoni

Intra-Active Inference I: Fundamentals
Ali Rahmjoo, Mahault Albarracin

Call for papers

Papers on all subjects and applications of active inference and related research areas are welcome. The workshop's focus is on the technical implementation of the ideas. Consequently, topics of interest include (but are not limited to):

Important dates

Submission Deadline: June 2, 2023 June 9, 2023
Acceptance Notification: July 14, 2023
Camera Ready Submission Deadline: September 1, 2023
Registration deadline: September 5, 2023
Workshop Date: September 13-15, 2023

Paper submissions

We welcome submissions of papers with up to 12 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 maximum 250 words. Contributions should be in PDF format and submitted via OpenReview (click here).

All submitted papers will undergo a rigorous double-blind peer review process, and be selected based on originality, quality, soundness, and relevance. Submitted papers need to be anonymized with the best of efforts. It is allowed to have a (non-anonymous) online pre-print. Accepted papers will be published in the proceedings in the Springer CCIS series.

Extended abstract submissions

We also welcome submissions of extended abstracts with up to 2 printed pages (excluding references and figures) in LNCS format (click here for details). These can cover the material of a journal paper published by the author in the past 12 months, or can be an abstract of late breaking results. Contributions should be in PDF format and submitted via OpenReview (click here). Extended abstracts will not be published in the proceedings, but can be accepted as presentations or as posters to the workshop.


Registration is closed.
The registration fee includes coffee breaks, lunch (Wed,Thu,Fri), and dinner (Wed,Thu).

By registering you agree to the Terms and Conditions.


The workshop will take place at the St Peter's Abbey, in Ghent, Belgium.

Travel information

At the main station of Ghent, Gent-Sint-Pieters, you will find railway links to all the cities in Belgium. This city also has a direct line to Brussels International Airport. Upon arrival, please go to floor -1 of the Brussels International Airport. From there you can take either a direct train to Ghent-Sint-Pieters (one every hour) or you can change trains in Brussels to get to Ghent. For further information about the beautiful city of Ghent, see visitgent.

Visa for Belgium

Please check the Belgian Embassy or Consulate in your own country to check if you need a visa to come to Belgium. Contact us in time if you need an invitation letter.


This event is made possible with the support of


IWAI 2023 is made possible thanks to the following people.


   General Chair: Tim Verbelen

   Local Organisation Chairs: Bart Dhoedt, Toon Van de Maele

   Technical Program Chairs: Daniela Cialfi, Martijn Wisse

   Communication Chair: Pablo Lanillos

Organisation committee

Christopher Buckley, University of Sussex, United Kingdom
Daniela Cialfi, Institute of Complex Systems (CNR); La Sapienza University of Rome, Italy
Pablo Lanillos, Donders Institute for Brain, Cognition and Behaviour, Netherlands
Maxwell Ramstead, VERSES, USA; and University College London, United Kingdom
Noor Sajid, University College London, United Kingdom
Hideaki Shimazaki, Kyoto University, Japan
Tim Verbelen, VERSES, USA
Martijn Wisse, Delft University of Technology, Netherlands

Programme committee

Anjali Bhat, University College London, United Kingdom
Christopher Buckley, University of Sussex, United Kingdom
Ozan Catal, VERSES, USA
Daniela Cialfi, Institute of Complex Systems (CNR); La Sapienza University of Rome, Italy
Lancelot Da Costa, Imperial College London, United Kingdom
Cedric De Boom, Statistiek Vlaanderen, Belgium
Bart Dhoedt, Ghent University, Belgium
Daniel Friedman, University of California, USA
Karl Friston, University College London, United Kingdom
Conor Heins, Max Planck Institute of Animal Behavior, Germany
Alex Kiefer, VERSES, USA
Brennan Klein, Northeastern University, USA
Pablo Lanillos, Donders Institute for Brain, Cognition and Behaviour, Netherlands
Christoph Mathys, Aarhus University, Denmark
Pietro Mazzaglia, Ghent University, Belgium
Ajith Anil Meera, Donders Institute for Brain, Cognition and Behaviour, Netherlands
Thomas Parr, University College London, United Kingdom
Corrado Pezzato, TU Delft, Netherlands
Maxwell Ramstead, VERSES, USA; and University College London, United Kingdom
Noor Sajid, University College London, United Kingdom
Dalton Sakthivadivel, VERSES, USA
Eli Sennesh, Northeastern University, USA
Panos Tigas, Oxford University, United Kingdom
Alexander Tschantz, VERSES, USA
Hideaki Shimazaki, Kyoto University, Japan
Ruben van Bergen, Radboud University, Netherlands
Toon Van de Maele, Ghent University, Belgium
Tim Verbelen, VERSES, USA
Martijn Wisse, Delft University of Technology, Netherlands

Previous editions

2020 - Ghent (virtual)
2021 - Bilbao (virtual)
2022 - Grenoble