We are searching for excellent ML+Robotics PhD students for five different projects at Intelligent Autonomous Systems Group, Computer Science, TU Darmstadt, TU Darmstadt, DFKI, hessian.AI !!! Apply using the link below: ias.informatik.tu-darmstadt.de/Jobs/OpenPosit… Enjoy #phdlife and Research in Germany (Research in Germany - Initiative of the BMBF).

CSIL has been accepted at NeurIPS Conference as a spotlight! ✨ Big thanks to my internship hosts Sandy and Nicolas at Google DeepMind Robotics We hope to share the code in the near future 🤖

I’m presenting CSIL at the poster session this morning, come find me at #1906! #NeurIPS2023 Sandy and I also open-sourced the implementation a few weeks back, you can find it at github.com/google-deepmin…

Active learning! 🔥Entropy-regularized control! ⚡️Sequential Monte Carlo! 🎲 Make sure to check it out

Scaling sample-efficient RL often relies on artisanal architectures (extra LayerNorm, etc) Daniel and Florian found a major issue with vanilla MLPs: the larger network weights slow optimization, so simply adding weight norm unlocks sample efficiency for much harder tasks! 🚀

Could geometric cues help improve goal inference in robotics? We explore this question at #RLDM today | Spot 86. Stop by if you're curious about bridging motion planning and intent prediction.

🚀 New preprint! Introducing XQC— a simple, well-conditioned actor-critic that achieves SOTA sample efficiency in #RL ✅ ~4.5× fewer parameters than SimbaV2 ✅ Scales to vision-based RL 👉 arxiv.org/pdf/2509.25174 Thanks to Florian Vogt Joe Watson Jan Peters hessian.AI DFKI