Michael Lutter

Research Engineer: Physics Simulation for RL bostondynamics.wd1.myworkdayjobs.com/Boston_Dynamic… Research Engineer: Atlas Behavior Learning bostondynamics.wd1.myworkdayjobs.com/Boston_Dynamic… Research Scientist: Atlas Behavior Learning bostondynamics.wd1.myworkdayjobs.com/Boston_Dynamic… 3/3

🚀 Boston Dynamics is growing! We’re hiring Research Scientists & Engineers to push the limits of humanoid robotics 🤖🧠. If you’re into reinforcement learning, large-scale physics simulation and dexterous manipulation - we’d love to talk. 1/3

If you know the ins and outs of CPU vs GPU simulation, the intricacies of contact detection, and get excited about building large-scale simulation for RL, this could be the perfect role for you. I’ll be at CoRL 2025 — let’s grab a coffee ☕ and chat! 2/3

My team at Boston Dynamics has open Research Scientist positions! We are hiring full-time and interns. If you are excited about RL & humanoids, we want to get to know you! Research Scientist: bostondynamics.wd1.myworkdayjobs.com/Boston_Dynamic… Research Scientist Intern: bostondynamics.wd1.myworkdayjobs.com/Boston_Dynamic…

@kevin_zakka @BostonDynamics @lucas_manuelli it was great to have you interning over the summer!

Today was the last of my internship at @BostonDynamics. I’m deeply grateful to my host @lucas_manuelli who has been an amazing mentor and friend this summer. I got to learn and absorb from world-class scientists and engineers over the last three months and it’s energized me as I head back to Berkeley to dive back into the Phd. Expect some cool research at the intersection of sim2real, humanoids and manipulation in the near future. PS: Was able to snag a pic with the most advanced AI hardware in the world ™ 🚀

I especially enjoyed the great demos of @CosimoDella lab.

#RSS2024 was a great! I enjoyed the talks, demos, posters and Delft. It was one of the best organized conferences. Looking forward to RSS 2025 in Los Angeles.

Great thread by @_bbelousov about my talk at the Embodiment Aware Robot Learning Workshop. Thanks for organizing the workshop.

The first day of #RSS2024 workshops was great. Looking forward to the next few days!

The all new electric Atlas is getting ready to do some real work ... 🤖 youtube.com/watch?v=29ECwE…

I guess no more backflips for you, HD Atlas 🤖🫡 youtube.com/watch?v=-9EM5_…

@KAbuibaid @ias_tudarmstadt @Jan_R_Peters Much of the content is also available in my Phd thesis available at tuprints.ulb.tu-darmstadt.de/20048/1/Phd_Th…

My Ph.D. thesis on combining domain knowledge and machine learning for robotics 🤖 🧠 got finally published in the Springer STAR series. Thanks for the great memories @ias_tudarmstadt & @Jan_R_Peters

If you are attending @ieeeiros, checkout this workshop on RL. I am looking forward to discuss the current advances and problems in RL. 🤖

@usuallyuseless @DPalenicek @ias_tudarmstadt @Hessian_AI @Jan_R_Peters @DBertsekas That is a good question. It definitely seems related but I could not fully grasp his reasoning when reading it for the first time. I need to look deeper into this. Thanks for the pointer, we were not aware of the paper.

@DPalenicek @ias_tudarmstadt @Hessian_AI @_mlutter @Jan_R_Peters Nice! I wonder how this relates to @DBertsekas recent rollout analysis: the *first* expansion (aka one-step lookahead) does a Newton step, while the latter reflect value iterations "only". This would explain the diminishing returns. athenasc.com/Newton'sMethod…

Very happy my first paper at @ias_tudarmstadt & @Hessian_AI got accepted at #ICLR2023. Thank you to my amazing co-authors @_mlutter, Joao Carvalho and @Jan_R_Peters. „Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning“ (openreview.net/forum?id=H4Ncs…).

Our model-based RL paper showing the diminishing returns 📉 of value expansion for off-policy algorithms led by @DPalenicek got accepted at #ICLR2023! 🎉🙃

The new Atlas Video has been released. It’s time to get started with athletic manipulation!

@antoniloq Thanks! Congrats to you as well. Your research on high speed drones was always exciting to watch. It was great to meet all finalists at the ERF and hear about their research.

A big congrats also to all other finalists and the ex-equo winner @_mlutter! All theses were really outstanding! Awesome to see so much great robotics research 🤖 happening in Europe!

Honored to receive the Georges Giralt PhD Award 🥇 (awarded to Europe's best thesis in Robotics 🤖) for my work on #learning vision-based high-speed #drone flight ✈️! Thanks to @davsca1 for the great supervision and all my collaborators! Thesis: tinyurl.com/yc33b73b @UZH_en

I am very honored to receive the 2022 Georges Giralt Ph.D. Award for the best robotics Ph.D. thesis in Europe from @eu_Robotics at the #ERF2022 . Thanks to @Jan_R_Peters and my colleagues at @ias_tudarmstadt that made this thesis possible! 😁🤖

After 5 successful years at @ias_tudarmstadt, it’s time to move. It was a fun and challenging time with many highlights. We made deep networks physically consistent and taught robots to juggle. Thanks to all colleagues and collaborators. 👋