Events Calendar

CS Colloquium: Sergey Levine (UC Berkeley) - Deep Learning for Decision Making and Control

Speaker: Sergey Levine, UC Berkeley

Talk Title: Deep Learning for Decision Making and Control

Series: CS Colloquium

Abstract: A remarkable feature of human and animal intelligence is the ability to autonomously acquire new behaviors. My work is concerned with designing algorithms that aim to bring this ability to robots and simulated characters. A central challenge in this field is to learn behaviors with representations that are sufficiently general and expressive to handle the wide range of motion skills that are necessary for real-world applications, such as general-purpose household robots. These representations must also be able to operate on raw, high-dimensional inputs and outputs, such as camera images, joint torques, and muscle activations. I will describe a class of guided policy search algorithms that tackle this challenge by transforming the task of learning control policies into a supervised learning problem, with supervision provided by simple, efficient trajectory-centric methods. I will show how this approach can be applied to a wide range of tasks, from locomotion and push recovery to robotic manipulation. I will also present new results on using deep convolutional neural networks to directly learn policies that combine visual perception and control, learning the entire mapping from rich visual stimuli to motor torques on a real robot. I will conclude by discussing future directions in deep sensorimotor learning and how advances in this emerging field can be applied to a range of other areas.

The lecture will be streamed through the dedicated link HERE.

Biography: Sergey Levine is a postdoctoral researcher working with Professor Pieter Abbeel at UC Berkeley. He completed his PhD in 2014 with Vladlen Koltun at Stanford University. His research focuses on robotics, machine learning, and computer graphics. In his PhD thesis, he developed a novel guided policy search algorithm for learning rich, expressive locomotion policies. In later work, this method enabled learning a range of robotic manipulation tasks, as well as end-to-end training of policies for perception and control. He has also developed algorithms for learning from demonstration, inverse reinforcement learning, and data-driven character animation.

Host: Computer Science Department

More Info: https://bluejeans.com/658994068

Location: Olin Hall of Engineering (OHE) - 132

Audiences: Everyone Is Invited

Contact: Assistant to CS chair

Event Link: https://bluejeans.com/658994068