Martin Riedmiller is a research scientist and team-lead at DeepMind, London. Before joining DeepMind fulltime in spring 2015, he held several professor positions in machine learning and neuro-informatics from 2002 to 2015 at Dortmund, Osnabrück and Freiburg University. From 1998 to 2009 he lead the robot soccer team ‘Brainstormers’ that participated in the internationally renowned RoboCup competitions. As an early proof of the power of neural reinforcement learning techniques, the Brainstormers won the world championships for five times in both simulation and real robot leagues. He has contributed over 20 years in the fields of reinforcement learning, neural networks and learning control systems. He is author and co-author of some early and ground-lying work on efficient and robust supervised learning and reinforcement learning algorithms, including work on one of the first deep reinforcement learning systems.
Keynote Title: Machines that learn by playing
Abstract: Our research is driven by the question, how intelligent agents can autonomously learn to control complex machines - like robots - when being provided only with minimal prior knowledge. In my talk I will give an overview on the exciting opportunities of Reinforcement Learning methods for control, with a focus on approaches that can learn in very general scenarios in a relatively small amount of interaction time. I will give examples of robots that learn to walk, reach goals or manipulate objects and highlight how we enable our agents to do so.