BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//hackathonmaxxing//EN
CALSCALE:GREGORIAN
X-WR-CALNAME:Hackathons in Berlin
BEGIN:VEVENT
UID:luma:evt-ExCPODdsAKgsLiQ@hackathonmaxxing
DTSTAMP:20261122T163357Z
DTSTART:20261123T173000Z
DTEND:20261123T190000Z
SUMMARY:BRISA Reading Group 07 - Estimate\, Don't Imitate: Reusing Differentiable State-Based Policies for Visuomotor Control
URL:https://lu.ma/zf7m6y1c?utm_source=hackathonmaxxing&utm_medium=referral&utm_campaign=berlin
LOCATION:Merantix AI Campus\, Berlin\, Germany
DESCRIPTION:Today\, we have a special one: Denis Shcherba presents his own paper\, Estimate\, Don’t Imitate: Reusing Differentiable State-Based Policies for Visuomotor Control (Shcherba et al.\, 2026)\, written right here in Berlin with Marc Toussaint (TU Berlin) and Wojciech Samek (Fraunhofer HHI). A rare chance to ask the author directly why things were done the way they were.\n\nIn simulation a robot can cheat: it knows exactly where every object is. Policies trained with this privileged state learn contact-rich behaviour well\, but a real robot only gets noisy camera images.\n\nThe usual fix is teacher-student distillation\, where a vision policy learns to copy the expert’s actions. That forces the student to do two jobs at once: work out the state from pixels\, and relearn a mapping from state to action that the expert already has.\n\nThis paper keeps the expert and only learns a visual state estimator.\n\nThe catch is that an error in the estimate can matter a lot or not at all\, depending on what the expert does with it. So the estimator is trained on two signals: plain state regression\, and an action-consistency loss backpropagated through the frozen\, differentiable expert.\n\nAcross five goal-conditioned manipulation tasks\, keeping the expert consistently beats direct pixel-to-action imitation trained on the same demonstrations. On a real Panda arm it reaches 76% success\, without retraining the expert.\n\nNo preparation needed.\n\nCome with questions for the author\, disagreements or your own view on end-to-end versus modular.\n\n🎟️ There are only a limited number of spots\, so we can keep the session personal and interactive. Please register early and only attend if you’ve received a ticket.\n\n📍 Hosted at the Merantix AI Campus on November 23rd. Doors open 18:30\, we start at 18:45.\n\n👋 New here? Join the community group - everything else gets announced there first. https://lu.ma/zf7m6y1c?utm_source=hackathonmaxxing&utm_medium=referral&utm_campaign=berlin
END:VEVENT
END:VCALENDAR
