Abstract: In this talk I will discuss what the practical part of reinforcement learning means to me, deep dive into environment design in simulation and the real world, and share lessons learned about getting reinforcement learning to work on robots.
Bio: Laura Graesser is a Senior Research Scientist in Robotics at Google DeepMind. Prior to that she was a Research Engineer also in Robotics at Google, where she has worked since 2018. Laura holds an MSc in Computer Science from NYU and a BA in Politics, Philosophy, and Economics from Oxford University. Her research interests include robotics, reinforcement learning, multi-agent systems, sim-to-real, and evolutionary strategies. For the past few years she has focused on getting robots to play table tennis in the real world. She also co-wrote a textbook, Foundation of Deep Reinforcement Learning.
16 сен 2024