Deep Reinforcement Learning Tutorial Site for PLDI 2019
In the recent years, there has been increased interest in the field of deep reinforcement learning (DRL), fuelled mainly by its performance in Atari Games and the win of AlphaGo over Mr. Lee Sedol, a Dan 9 Go player. Unlike supervised learning, reinforcement learning does not require labeled data. Here the agent learns through its interaction with the environment. DRL combines the deep learning for sensory processing along with reinforcement learning algorithms. This tutorial introduces some of the most popular and successful DRL algorithms. We will start with an introduction to different learning paradigms and how DRL differs from them. We will also introduce the OpenAI reinforcement learning environment. The two major RL methods: value-based methods and policy-based methods will be explored. We will cover the Deep Q Network and use it to solve a discrete action space environment. Policy gradient methods will also be explored with a special emphasis on continuous action space and multi-agent environment. Finally, we will cover the pros and cons of different algorithms and proposed variations in them. The Tutorial will end with some open research problems in the field of DRL.
The tutorial will cover the following sessions of 30 minutes each:
The audience should be aware of the basic deep learning algorithms, specifically Convolutional Neural Networks and Stochastic Gradient. Basic knowledge of Python language and one of the deep learning frameworks such as PyTorch or TensorFlow will be useful.
Amita Kapoor is Associate Professor in the Department of Electronics, SRCASW, University of Delhi. She has been actively teaching neural networks for the last twenty years. She is the recipient of the prestigious DAAD fellowship to pursue a part of her research work in Karlsruhe Institute of Technology, Karlsruhe, Germany. She had been awarded Best Presentation Award at International Conference Photonics 2008 for her paper. She has more than 40 research publications in international journals and conferences. Her present research areas include Machine Learning, Artificial Intelligence, Neural Networks, Robotics, Buddhism (Philosophy and Psychology) and Ethics in AI. She is also the author of the book Tensorflow 1.x Deep Learning Cookbook by Packt Publishers.
Armando creates AI empowered products by leveraging reinforcement learning, deep learning, machine learning, distributed computing, and computational methods. Armando has provided thought leadership as Chief Data Scientist and Director at small and large organizations. Armando has been advising high-tech AI-based startups. Armando has authored books titled Python Data Analysis - Second Edition and Mastering TensorFlow. He has published research in international journals and conferences.