Author: admin

When: Thursday Oct 18 @ 1:00pm – 2:00 pm

Where: BA 5281

When: Tuesday Sept 25 @ 1:15pm – 2:15 pm

Where: GB 167

Please note that the Meet & Eat will follow immediately after the talk which will be held on Sep 25th, at 12pm-1pm in GB202. For more information regarding the talk, please visit  https://www.mie.utoronto.ca/events/or-seminar-series-james-luedtke-university-of-wisconsin-madison/

Who: Michael Gimelfarb, Ph.D. candidate, University of Toronto

When: Thursday, September 20th @ 12:00pm – 1:00pm

Where: MB101

Bio-sketch: Michael Gimelfarb is a full-time PhD student in MIE since September 2017, supervised jointly by Professor Chi-Guhn Lee and Professor Scott Sanner. He received his BBA in Finance from the Schulich School of Business in 2014, and his MASc from MIE in 2016, where his thesis focused on the theoretical analysis of the Thompson sampling algorithm applied to queuing control problems. His current research focuses on the application of Bayesian methods and deep learning techniques to reinforcement learning problems. Some of his current and recent work includes reward shaping, decision tree classification using bandits, and automated curriculum learning.

Abstract:  Potential based reward shaping is a powerful technique for accelerating convergence of reinforcement learning algorithms. Typically, such information includes an estimate of the optimal value function and is often provided by a human expert or other sources of domain knowledge. However, this information is often biased or inaccurate and can mislead many reinforcement learning algorithms. In this paper, we apply Bayesian Model Combination with multiple experts in a way which learns to trust the best combination of experts as training progresses. This approach is both computationally efficient and general, and is shown numerically to improve convergence of various reinforcement learning algorithms across many domains.

When: Thursday Sept 13 @ 1:30pm – 2:00 pm

Where: BA8256

Bio-sketch: Phebe Vayanos is an Assistant Professor of Industrial & Systems Engineering and Computer Science at the University of Southern California, and Associate Director of the CAIS Center for Artificial Intelligence in Society. Prior to joining USC, she was a lecturer in the Operations Research and Statistics Group at the MIT Sloan School of Management and a postdoctoral research associate in the Operations Research Center at MIT. She holds a Ph.D. degree in Operations Research and a MEng degree in Electrical & Electronic Engineering, both from Imperial College London.

Her research aims to address fundamental questions arising in data-driven integer and robust optimization, and game theory. Her work is motivated by decision-making and resource allocation problems that are important for social good, such as those arising in public health, public safety and security, biodiversity preservation, education, and energy. Her aim is to advance research in Operations Research and Artificial Intelligence in a manner that will benefit society and in particular low resource communities and others that have not benefited from these recent developments.