PhD student Bayesian Machine Learning & Active Inference @TUeindhoven . Football & Futsal enthousiast
Eindhoven, Nederland
Joined February 2022
- Tweets37
- Following77
- Followers40
- Likes65
Wouter Nuijten retweeted
Our own @wouterwln & colleagues @ UAI: "What Type of Inference is Active Inference?"
They show it's just variational inference + explicit corrections: one makes planning, the others make curiosity.
Ambiguous world? Curiosity wins. 🔗
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. 👇
Our policy-based inference outperforms plan-based methods under stochastic transitions and scales to MiniGrid where tabular active inference struggles.
📄 Paper: openreview.net/pdf?id=Kzm8I1…💻 JAX Code: github.com/biaslab/Epistemic…
#ActiveInference #TMLR #MachineLearning
Kudos to the TMLR team for a smooth submission process, and to my coauthors @ThijsvdLaar and @bertdv0
Wouter Nuijten retweeted
Looking for prospective students & collaborators to work towards *An Agent Foundation Model*! 👨💻👩💻
Keywords: Active model discovery, active learning & model based planning.
More details:
lancelotdacosta.com/research (bottom of page).
If you’re interested, get in touch! 💡
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
Wouter Nuijten retweeted
🏆 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: arxiv.org/abs/2508.02197
Code: github.com/biaslab/EFEasVFE
#IWAI2025 #RxInfer #Bayesian
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 github.com/lazydynamics/Gear…. We chose to make it public, so let me know what you think!
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?
This is what we ask ourselves in our latest paper (arxiv.org/abs/2508.02197), where we solve Minigrid environments with Active Inference. (Spoiler, it works!)
Code available at github.com/biaslab/EFEasVFE
Done together with @mlmykola , @ThijsvdLaar and @bertdv0
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 retweeted
Agreed with @fchollet on FEP (t.ly/s4gMV), 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:
Wouter Nuijten retweeted
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)
Wouter Nuijten retweeted
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 rxinfer.com now. This time for real (probably).
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.
Wouter Nuijten retweeted
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.
📄 openreview.net/pdf?id=QBbc0L…
💻 github.com/biaslab/GradientF…
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 ;)
openreview.net/pdf?id=QBbc0L…
Also, this week I am at @iwai_ws in Oxford to talk about Active Inference, so hit me up for a Free Energy Chat ;)
A couple of weeks ago, I talked at @JuliaConOrg about one of my packages. The video is available here: youtu.be/7DFmyzgNeGQ?si=ukmT…