Title: Generative Control, Action Chunking, and Moravec’s Paradox
Speaker: Prof. Max Simchowitz (CMU)
Location: Nvidia Auditorium (link)
Attendance Link: https://tinyurl.com/robosem-win-26
Time: Friday Feb 27th, 3:00-4:00PM
Abstract:
Moravec’s Paradox observes that AI systems have struggled far more with learning physical actions than symbolic reasoning. Yet just recently, there has been a tremendous increase in the capability of AI-driven robotic systems, reminiscent of the early improvements in language modeling capabilities a few years ago. In this talk, we provide mathematical evidence that learning in continuous-control settings, like robotics, can be exponentially more challenging than in discrete settings, like language, unless certain key algorithmic design choices are made - effectively, mathematical evidence for Moravec’s claim. We then show that two of the key innovations in modern robot learning - action chunking, and the use of generative models, such as diffusion models, to parametrize robot actions - can be interpreted as directly mitigating the mechanisms underlying this difficulty. Our perspective runs contrary to many popular justifications for the two methods, such as capturing multi-modality present in mixed-quality training data. Finally, if time permits, we will describe a new family of interventions, at the level of deep learning optimization, that provide yet another lever for addressing the same challenges.
Bio:
Dr. Max Simchowitz is an assistant professor at the Machine Learning Department at Carnegie Mellon University with a courtesy appointment in the Robotics Institute. His work studies theoretical foundations and new methodologies for machine learning problems with an interactive, sequential, or dynamical component, currently focusing on reinforcement learning and applications to robotics. His past work has ranged broadly across control, theoretical reinforcement learning, optimization and algorithmic fairness. He received his PhD from University of California, Berkeley in 2021 under Ben Recht and Michael I. Jordan, and completed his postdoctoral research under Russ Tedrake in the Robot Locomotion Group at MIT. His work has been recognized with an ICML 2018 Best Paper Award, ICML 2022 Outstanding Paper Award, and RSS 2023 and ICRA 2024 Best Paper Finalist designations.
Please visit https://stanfordasl.github.io/robotics_seminar/ for this quarter’s lineup of speakers. Although we encourage live in-person attendance, recordings of talks will be posted also.
If you’re interested, you’re welcome to join Max for lunch at Blend Cafe at 12 PM. Please let Hao Li (li2053@stanford.edu) know if you plan to join.