Tutorial Workshop: Dileep Kalathil: Reinforcement Learning – Algorithms and Applications

April 3, 2020

2:00 pm - 5:00 pm

Online via zoom

Tutorial presentation slides are available here:

Dr. Dileep Kalathil, assistant professor in the Dept. of Electrical & Computer Engineering at Texas A&M University led a tutorial workshop on Reinforcement Learning: Algorithms and Applications, The workshop covered the fundamental theory and concepts, state-of-the-art algorithms, and successful applications of reinforcement learning.

Workshop background and topics

Most engineering systems are moving towards an autonomous future. One key aspect of any autonomous system is the intelligent agents who can adaptively learn and take sequential decisions in uncertain and stochastic environments. Reinforcement Learning (RL) is a class of machine learning that addresses the problem of learning the optimal control policies for such autonomous systems. RL is extremely useful in a large number of areas, starting from the classical stochastic control problems to most recent applications in robotics, drones, games, healthcare and self-driving cars. This tutorial will cover the fundamental theory and concepts, state-of-the-art algorithms, and successful applications of reinforcement learning. In particular, we will discuss: (i) Markov Decision Process (MDP) as a simple yet powerful abstraction for modeling real-world control problems, (ii) Q-Learning algorithm to solve RL problems, (iii) Deep Q-Learning algorithms, (iv) Policy gradient based deep RL algorithms for continuous control, and (v) Imitation learning algorithms.

Workshop organization

The workshop is split into two 1.5-hour lecture style sessions with a short break in between. The instructor will give two programming assignments after the lecture, based on the topics discussed, and also provide the Jupyter notebooks for those assignments.

Registration

Registration is no longer required

Background knowledge advised for participants 

Participants must have at least a basic understanding of undergraduate level probability. Knowledge of machine learning concepts from supervised learning is recommended. Some understanding of neural network and deep learning would be helpful.

Biography of the workshop leader

Dileep Kalathil is an assistant professor in the Department of Electrical and Computer Engineering at Texas A&M University. His main research area is reinforcement learning, with applications in cyber-physical systems, intelligent transportation systems and power systems. In particular, his research addresses three fundamental problems in RL: (i) How to develop data efficient RL algorithms? (ii) How to develop safe and robust RL algorithms? and (iii) How to develop scalable multi-agent RL algorithms? Before joining TAMU, he was a postdoctoral researcher in the EECS department at UC Berkeley. He received his PhD from University of Southern California (USC) in 2014 where he won the best PhD Dissertation Prize in the Department of Electrical Engineering. He received an M. Tech. from IIT Madras where he won the award for the best academic performance in the Electrical Engineering Department.