The Robot Learning Seminar Series is a regular series of in-person seminars at Imperial College London, hosted by Edward Johns, Director of the Robot Learning Lab. For more information, please visit www.robot-learning.uk/seminar-series.
Speaker: Markus Wulfmeier (Google DeepMind)
Title: Reinforcement Learning in the Age of Large Data
Date: Thursday 20th June 2024
Abstract: Recent, vast progress in artificial intelligence, in particular deep learning for vision and language processing, rely on immense datasets and the imitation of existing knowledge. It is only natural to ask about the role of reinforcement learning given the resulting research environment and practical applications. In this talk, I will go back to the fundamental strengths of RL and explore how they will remain impactful in the coming years. Two example projects will provide empirical support for this journey. First, our team's recent advancements in autonomous robot soccer provide the foundation to talk about data availability and generation in complex control domains. And second, I will use route recommendation in Google Maps, a domain that impacts billions of users, to discuss the role of RL for optimization with existing datasets.
Biography: Markus Wulfmeier is a researcher in machine learning and robotics at Google DeepMind with a focus on fundamental and applied research on reinforcement and imitation learning. His work aims at efficiently scalable algorithms applicable across a variety of real-world applications including robotic locomotion, manipulation, navigation, and communication. Markus was a postdoctoral research scientist at the Oxford Robotics Institute and a member of Oxford University’s New College where he completed his PhD. Over the years, he has held visiting scholar positions with UC Berkeley, MIT, and ETH.
20 июн 2024
