Deep Reinforcement Learning, Decision Making, and Control
ICML 2017 Tutorial
Deep learning methods, which combine high-capacity neural network models with simple and scalable training algorithms, have made a tremendous impact across a range of supervised learning domains, including computer vision, speech recognition, and natural language processing. This success has been enabled by the ability of deep networks to capture complex, high-dimensional functions and learn flexible distributed representations. Can this capability be brought to bear on real-world decision making and control problems, where the machine must not only classify complex sensory patterns, but choose actions and reason about their long-term consequences?
Decision making and control problems lack the close supervision present in more classic deep learning applications, and present a number of challenges that necessitate new algorithmic developments. In this tutorial, we will cover the foundational theory of reinforcement and optimal control as it relates to deep reinforcement learning, discuss a number of recent results on extending deep learning into decision making and control, including model-based algorithms, imitation learning, and inverse reinforcement learning, and explore the frontiers and limitations of current deep reinforcement learning algorithms.
Sergey Levine is an Assistant Professor in the Department of Electrical Engineering and Computer Sciences at UC Berkeley. His research focuses on the intersection between control and machine learning, with the aim of developing algorithms and techniques that can endow machines with the ability to autonomously acquire the skills for executing complex tasks. In particular, he is interested in how learning can be used to acquire complex behavioral skills, in order to endow machines with greater autonomy and intelligence.
Chelsea Finn is a PhD student at UC Berkeley and part of Berkeley AI Research (BAIR). Her research is at the intersection of machine learning, perception, and control for robotics. In particular, she is interested in how learning algorithms can enable robots to autonomously acquire complex sensorimotor skills. She received her Bachelors in EECS at MIT, and has also spent time working at Google Brain.