Wouter Nuijten

PhD student Bayesian Machine Learning & Active Inference @TUeindhoven . Football & Futsal enthousiast

[Wouter Nuijten @wouterwln]

Kudos to the TMLR team for a smooth submission process, and to my coauthors @ThijsvdLaar and @bertdv0

[Wouter Nuijten @wouterwln]

Out now in TMLR! 🚀

We formalize how epistemic priors transform Expected Free Energy minimization into a standard variational objective.

This allows us to frame planning as a continuous variational optimization problem, moving away from combinatorial tree search. 👇

[Wouter Nuijten @wouterwln]

Our policy-based inference outperforms plan-based methods under stochastic transitions and scales to MiniGrid where tabular active inference struggles.

📄 Paper: https://t.co/Do0GpDG27A💻 JAX Code: https://t.co/esAIPsMngm
#ActiveInference #TMLR #MachineLearning

[Lancelot Da Costa @lancelotdacosta]

Looking for prospective students & collaborators to work towards *An Agent Foundation Model*! 👨‍💻👩‍💻
Keywords: Active model discovery, active learning & model based planning.
More details:
https://t.co/vEOQOzVAls (bottom of page).
If you’re interested, get in touch! 💡

[Wouter Nuijten @wouterwln]

I'm in Copenhagen for @EurIPSConf this week, showing some work at the Epistemic Intelligence in ML workshop. If you're in town and want to link up, let me know!
​#EurIPS #MachineLearning #AI #Copenhagen

[Lazy Dynamics @LazyDynamics]

🏆 Best Technical Paper at @iwai_ws!
Recasting EFE planning as Variational Inference → sample-efficient Active Inference agents that actually run.
Built in RxInfer. Won by @wouterwln.

Paper: https://t.co/ybnLLZsdL6
Code: https://t.co/gCGWi0SKAQ

#IWAI2025 #RxInfer #Bayesian

[Wouter Nuijten @wouterwln]

Recently at @lazydynamics, we needed a fine-grained scheduler, coupled to the machine clock, to build our multi-scale agents. To streamline development, I built `Gears.jl`, available now at https://t.co/bdOIEpBbpw. We chose to make it public, so let me know what you think!

[Wouter Nuijten @wouterwln]

What's even nicer: because our method injects priors locally, everything still works within @ReactiveBayes ' RxInfer.jl using message passing. Special thanks to my colleagues at @LazyDynamics for making this possible!

[Wouter Nuijten @wouterwln]

In Active Inference, a lot of time is spent on computing Expected Free Energy. What if we could tweak the generative model such that EFE can be minimised with traditional variational inference methods?

[Wouter Nuijten @wouterwln]

This is what we ask ourselves in our latest paper (https://t.co/nH8BvgdvAp), where we solve Minigrid environments with Active Inference. (Spoiler, it works!)
Code available at https://t.co/3W3BzTaPkX
Done together with @mlmykola , @ThijsvdLaar and @bertdv0

[Bert de Vries @bertdv0]

Agreed with @fchollet on FEP (https://t.co/uiCiCLoLnM), but FEP is more than a pretty good idea, and there are more benefits to realizing an agent as an active inference (AIF) process beyond active data selection. I will mention a few below:

[Bert de Vries @bertdv0]

New paper alert! Active Inference (AIF) agents score policy candidates using a cost function called the Expected Free Energy (EFE), which has many desirable features, such as a parameter-free balance between information-seeking and goal-driven behavior. (1/4)

[ReactiveBayes @ReactiveBayes]

Turns out .ml doesn’t just stand for machine learning - it also means maybe lost :/

But hey, every project needs its "we lost our domain" story. Our just happened on Friday. Find us at https://t.co/i0XNOp2jNz now. This time for real (probably).

[Wouter Nuijten @wouterwln]

Catch me at @NeurIPSConf in Vancouver, BC this week! I will be at the conference all week, so feel free to hit me up for a drink (or five)! Saturday, I will present a poster at the Bayesian Decision Making workshop.

[ReactiveBayes @ReactiveBayes]

Exciting work from @ReactiveBayes developers (@mlmykola, @wouterwln, @bvdmitri, İsmail Şenöz) presented at the NeurIPS Bayesian Workshop!

Riemannian Black Box VI (RBBVI) tackles non-differentiable, costly models.

📄 https://t.co/z57YTPkBxy
💻 https://t.co/tUExXuber7

[Wouter Nuijten @wouterwln]

This work is together with @mlmykola , @bvdmitri , Ismail Senöz and @bertdv0

[Wouter Nuijten @wouterwln]

Absolutely thrilled to announce that our work “Riemannian Black Box Variational Inference” has been accepted at the NeurIPS Workshop on Bayesian Decision-Making and Uncertainty! See you in December in Vancouver ;)

https://t.co/RXfNBIwQ4F

[Wouter Nuijten @wouterwln]

Also, this week I am at @iwai_ws in Oxford to talk about Active Inference, so hit me up for a Free Energy Chat ;)

[Wouter Nuijten @wouterwln]

A couple of weeks ago, I talked at @JuliaConOrg about one of my packages. The video is available here: https://t.co/VD70LkBoAb

[ReactiveBayes @ReactiveBayes]

🚀 Calling all Bayesian enthusiasts! @ReactiveBayes needs YOU to shape the future of reactive, efficient & scalable inference. Join us in building Bayesian-driven autonomous agents with RxInfer.jl. Fork, contribute, discuss at https://t.co/lmYxHMlgnC
#BayesianInference #Julia