Date & time
Tuesday, May 26, 2026
10 a.m. – 12 p.m.
10 a.m. – 12 p.m.
Conferences & lectures
Share this event:
From Control Theory to Reinforcement Learning: A Unified Tutorial
Presented by Dr. Aditya Mahajan, Dept. of Electrical & Computer Engineering at McGill University
Speaker(s)
Dr. Aditya Mahajan
Cost
This event is free.
Contact
Where
John Molson Building
1450 Guy St.
Room 14.250
Accessible location
Yes - See details
In this talk, we provide an overview of sequential decision-making. We first review Markov decision processes and dynamic programming, which recast optimization over time into a sequence of nested one-step optimization problems. We then outline the main ideas of reinforcement learning and explain how they provide an efficient approximate solution to these dynamic programs.
Bio
Aditya Mahajan is Professor of Electrical and Computer Engineering at McGill University, Montreal, Canada. He is a member of the McGill Center for Intelligent Machines (CIM), Mila - Québec AI Institute, International Laboratory for Learning Systems (ILLS), and Groupe d’études et de recherche en analyse des décisions (GERAD). He received the B.Tech degree in Electrical Engineering from the Indian Institute of Technology, Kanpur, India and the MS and PhD degrees in Electrical Engineering and Computer Science from the University of Michigan, Ann Arbor, USA. He has held visiting appointments at the University of California, Berkeley and the University of Paris-Saclay.
He is a senior member of the IEEE and a member of Professional Engineers Ontario. He currently serves as Associate Editor of Springer Mathematics of Control, Signal, and Systems. In the past, he has served as an Associate Editor of IEEE Transactions on Automatic Control IEEE Control Systems Letters, and IEEE Control Systems Society Conference Editorial Board.He is the recipient of the 2015 George Axelby Outstanding Paper Award, the 2016 NSERC Discovery Accelerator Award, the 2014 CDC Best Student Paper Award (as supervisor), and the 2016 NecSys Best Student Paper Award (as supervisor).
His principal research interests include decentralized stochastic control, team theory, reinforcement learning, multi-armed bandits and information theory.