Introducing <tt>ActiveInference.jl</tt>: A Julia Library for Simulation and Parameter Estimation with Active Inference Models

We introduce a new software package for the Julia programming language, the library ActiveInference.jl. To make active inference agents with Partially Observable Markov Decision Process (POMDP) generative models available to the growing research community using Julia, we re-implemented the pymdp lib...

Full description

Saved in:
Bibliographic Details
Main Authors: Samuel William Nehrer, Jonathan Ehrenreich Laursen, Conor Heins, Karl Friston, Christoph Mathys, Peter Thestrup Waade
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Entropy
Subjects:
Online Access:https://www.mdpi.com/1099-4300/27/1/62
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832588545584267264
author Samuel William Nehrer
Jonathan Ehrenreich Laursen
Conor Heins
Karl Friston
Christoph Mathys
Peter Thestrup Waade
author_facet Samuel William Nehrer
Jonathan Ehrenreich Laursen
Conor Heins
Karl Friston
Christoph Mathys
Peter Thestrup Waade
author_sort Samuel William Nehrer
collection DOAJ
description We introduce a new software package for the Julia programming language, the library ActiveInference.jl. To make active inference agents with Partially Observable Markov Decision Process (POMDP) generative models available to the growing research community using Julia, we re-implemented the pymdp library for Python. ActiveInference.jl is compatible with cutting-edge Julia libraries designed for cognitive and behavioural modelling, as it is used in computational psychiatry, cognitive science and neuroscience. This means that POMDP active inference models can now be easily fit to empirically observed behaviour using sampling, as well as variational methods. In this article, we show how ActiveInference.jl makes building POMDP active inference models straightforward, and how it enables researchers to use them for simulation, as well as fitting them to data or performing a model comparison.
format Article
id doaj-art-4168291e60994642b3b1621b2c8a3954
institution Kabale University
issn 1099-4300
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Entropy
spelling doaj-art-4168291e60994642b3b1621b2c8a39542025-01-24T13:31:52ZengMDPI AGEntropy1099-43002025-01-012716210.3390/e27010062Introducing <tt>ActiveInference.jl</tt>: A Julia Library for Simulation and Parameter Estimation with Active Inference ModelsSamuel William Nehrer0Jonathan Ehrenreich Laursen1Conor Heins2Karl Friston3Christoph Mathys4Peter Thestrup Waade5School of Culture and Communication, Aarhus University, 8000 Aarhus, DenmarkSchool of Culture and Communication, Aarhus University, 8000 Aarhus, DenmarkDepartment of Collective Behaviour, Max Planck Institute of Animal Behavior, D-78457 Konstanz, GermanyVERSES Research Lab., Los Angeles, CA 90016, USAInteracting Minds Centre, Aarhus University, 8000 Aarhus, DenmarkInteracting Minds Centre, Aarhus University, 8000 Aarhus, DenmarkWe introduce a new software package for the Julia programming language, the library ActiveInference.jl. To make active inference agents with Partially Observable Markov Decision Process (POMDP) generative models available to the growing research community using Julia, we re-implemented the pymdp library for Python. ActiveInference.jl is compatible with cutting-edge Julia libraries designed for cognitive and behavioural modelling, as it is used in computational psychiatry, cognitive science and neuroscience. This means that POMDP active inference models can now be easily fit to empirically observed behaviour using sampling, as well as variational methods. In this article, we show how ActiveInference.jl makes building POMDP active inference models straightforward, and how it enables researchers to use them for simulation, as well as fitting them to data or performing a model comparison.https://www.mdpi.com/1099-4300/27/1/62active inferencefree energy principlepredictive processingMarkov decision processcognitive modellingJulia
spellingShingle Samuel William Nehrer
Jonathan Ehrenreich Laursen
Conor Heins
Karl Friston
Christoph Mathys
Peter Thestrup Waade
Introducing <tt>ActiveInference.jl</tt>: A Julia Library for Simulation and Parameter Estimation with Active Inference Models
Entropy
active inference
free energy principle
predictive processing
Markov decision process
cognitive modelling
Julia
title Introducing <tt>ActiveInference.jl</tt>: A Julia Library for Simulation and Parameter Estimation with Active Inference Models
title_full Introducing <tt>ActiveInference.jl</tt>: A Julia Library for Simulation and Parameter Estimation with Active Inference Models
title_fullStr Introducing <tt>ActiveInference.jl</tt>: A Julia Library for Simulation and Parameter Estimation with Active Inference Models
title_full_unstemmed Introducing <tt>ActiveInference.jl</tt>: A Julia Library for Simulation and Parameter Estimation with Active Inference Models
title_short Introducing <tt>ActiveInference.jl</tt>: A Julia Library for Simulation and Parameter Estimation with Active Inference Models
title_sort introducing tt activeinference jl tt a julia library for simulation and parameter estimation with active inference models
topic active inference
free energy principle
predictive processing
Markov decision process
cognitive modelling
Julia
url https://www.mdpi.com/1099-4300/27/1/62
work_keys_str_mv AT samuelwilliamnehrer introducingttactiveinferencejlttajulialibraryforsimulationandparameterestimationwithactiveinferencemodels
AT jonathanehrenreichlaursen introducingttactiveinferencejlttajulialibraryforsimulationandparameterestimationwithactiveinferencemodels
AT conorheins introducingttactiveinferencejlttajulialibraryforsimulationandparameterestimationwithactiveinferencemodels
AT karlfriston introducingttactiveinferencejlttajulialibraryforsimulationandparameterestimationwithactiveinferencemodels
AT christophmathys introducingttactiveinferencejlttajulialibraryforsimulationandparameterestimationwithactiveinferencemodels
AT peterthestrupwaade introducingttactiveinferencejlttajulialibraryforsimulationandparameterestimationwithactiveinferencemodels