Andrey Kolobov

关于

I am a Principal Research Manager at MSR Redmond, leading MSR’s Special Physically Embodied AI and Robotics team (SPEAR) that focuses on physical AI for robotic manipulation. My current research revolves around the following overarching questions: (1) How can robots use the prior knowledge encoded in multimodal models as well as physical interaction-specific inductive biases for data-efficient learning to act during (lifelong) post-training? (2) What type of knowledge should we pre-train into physical AI models to enable this kind of efficient decision learning? Despite focusing on robotics, I believe that the very same questions are fundamental to unlocking the potential of non-robotic and even non-embodied decision-making agents, including those based on text-only LLMs.

In the past, I worked on topics ranging from decision-making and atmosphere modelling for autonomous sailplane UAVs to scheduling algorithms for Bing’s next-generation Web crawler to understanding the solution properties of MDPs with irrecoverable failure states (opens in new tab).

I received a CS Ph.D. from the University of Washington – Seattle and a double B.A. in CS and applied mathematics from UC Berkeley.