flâneur

Supervised Policy Learning for Real Robots

supervised-robot-learning.github.io · 448 words · saved by 2 readers

RSS 2024 Tutorial on Supervised Policy Learning for Real Robots. Friday, July 19 Afternoon (2PM - 6PM Central European time, 8AM - 12AM Eastern Time).

Overview Creating robots that can perform a wide variety of complex tasks, with generalization to unstructured real-world settings, has long been a north star for the field. Recently, advances in machine learning and data collection frameworks have allowed supervised learning-from-demonstration approaches to take significant strides in this direction (e.g. Diffusion policy, RT-1/2/X, or Dobb-E). In this paradigm, policy learning is cast as a supervised learning problem to learn a mapping from raw observations to demonstrated actions. So what matters for Supervised Policy Learning (SPL)?…

saved by

related reading