Michael Drolet

PhD student at @ias_tudarmstadt | Interested in latent representations & robotics

[Aditya Bhatt @aditya_bhatt]

A first glimpse of the wildest robotics project of my PhD.

🛹 The Blind Skateboarder 🛹

No vision. No markers.

Paper, code, weights — coming soon. And we have more. 😉

[Michael Drolet @mdrolet01]

Cool work :) We recently explored a similar GPT-style approach for humanoids here https://t.co/eWw8cZjFOk

[NVIDIA AI @NVIDIAAI]

Most motion papers tailor one controller to one specific task. This year at SIGGRAPH, our research team asks: can motor control itself be pretrained and reused?

Generative Pretrained Controllers, or GPC, turn motor skills into a vocabulary of discrete tokens and train a transformer-based generative controller through next-token prediction. Just like GPT, the same pretrained controller can then be fine-tuned to solve new tasks.

Trained on 600+ hours of motion, GPC runs in real-time inside a physics simulation, producing natural and physically grounded behaviors for interactive control.

[Michael Drolet @mdrolet01]

Interested in discrete latents?

I’ll be presenting a new method for training discrete VAEs at ICLR in Rio 🇧🇷

📍 Pavilion 3, P3-605
🗓 Thu, Apr 23 @ 11:15
More details below 👇

[Michael Drolet @mdrolet01]

DAPS: Discrete Variational Autoencoding via Policy Search (accepted @iclr_conf)

A principled way to train discrete autoregressive encoders —
without straight-through gradients.

Entropy reg. + KL trust region
for stable training and compact latents.
🔗 https://t.co/SJgESLqTrf

[Michael Drolet @mdrolet01]

Huge thanks to my co-authors:
@firasalhafez, @aditya_bhatt, @Jan_R_Peters, and @OlegArenz.

Grateful for the support from TU Darmstadt, DFG, and Hessian AI.

If you'll be at ICLR (Rio 🇧���), come say hi!
Questions & feedback welcome 🙏

@ias_tudarmstadt #ICLR2026

[Michael Drolet @mdrolet01]

DAPS: Discrete Variational Autoencoding via Policy Search (accepted @iclr_conf)

A principled way to train discrete autoregressive encoders —
without straight-through gradients.

Entropy reg. + KL trust region
for stable training and compact latents.
🔗 https://t.co/SJgESLqTrf

[Michael Drolet @mdrolet01]

Step 3: Optimal target distribution.

Solve a KL-constrained optimization problem
to get a closed-form non-parametric target q*.
Update the parametric encoder toward q*.

[Tim Schneider @timschneider94]

Proud to share our latest work, accepted at @iclr_conf 2026: APPLE! 🍎

TL;DR: APPLE is a novel reinforcement learning framework for solving active perception problems.

#ICLR2026 #Robotics #MachineLearning #ActivePerception #RL
@ias_tudarmstadt

[Ahmed Hendawy | أحمد هنداوي @AHendawy19]

🧵 Accepted at @iclr_conf !

Target networks stabilize bootstrapping in RL 🛡️
But induce slow-moving targets 🐢

Online networks adapt fast ⚡
But can diverge with function approximation 💥

𝗠𝗜𝗡𝗧𝗢🌿 uses the online network 𝗼𝗻𝗹𝘆 𝗶𝗳 𝗶𝘁 𝗰𝗮𝗻 — yielding faster and more stable RL.

Here’s how 👇

[Michael Drolet @mdrolet01]

@davide_tateo @liu_puze Thank you Davide for your mentorship. You will be missed!

[Michael Drolet @mdrolet01]

@hbouammar I had a similar thought when I came across this paper recently.. https://t.co/ltXyVszmfQ

[Firas Al-Hafez @firasalhafez]

🚀 We’re releasing #LocoMuJoCo2 — An extensive library for whole-body imitation & RL.

🔥 Highlights:
- Supports MuJoCo & MJX
- Clean JAX impl of PPO, GAIL, AMP, DeepMimic
- 22K+ trajectories per humanoid
- Add your humanoid easily

🔗 https://t.co/EAYIjjh23d

🧵Details 👇

[Michael Drolet @mdrolet01]

@davide_tateo @Theo_Vincent_ @nabokovtimothy the best framework 𝘣𝘦𝘩𝘪𝘯𝘥 𝘫𝘢𝘹

[Intelligent Autonomous Systems Group @ias_tudarmstadt]

Something exciting just arrived at our lab! Here's a hint: precision mechanics, intricate wiring, and a touch of power. What could it be?
A) High-end lab equipment
B) Experimental space probe component
C) Something that might walk past you in the hallway.
Share your guesses!

[Michael Drolet @mdrolet01]

@asurobot @davide_tateo @_bbelousov @SimonStepputtis Will always have a special place in my heart for IRL... Similar research, just in a different country 🙂 We’ve got some cool humanoids on the way—exciting times!!

[Michael Drolet @mdrolet01]

@davide_tateo @_bbelousov @Boris haha. it's my first day with x.. rookie mistake