Seminar Schedule

May 26th, 2021

11:30am – 12:00pm EST

Houssam Nassif, Amazon

Solving Inverse Reinforcement Learning, Bootstrapping Bandits

May 26th, 2021

11:00am – 11:30am EST

Zhaoran Wang, Northwestern University

Is Pessimism Provably Efficient for Offline RL?

May 26th, 2021

10:30am – 11:00am EST

Zhuoran Yang, Princeton University

On Function Approximation in Reinforcement Learning: Optimism in the Face of Large State Space

May 13th, 2021

10:30pm – 11:30pm EST

Guanjie Zheng, Shanghai Jiao Tong University

Improving Urban Traffic Signal Control via Reinforcement Learning

April 29th, 2021

9:00pm – 10:00pm EST

Keith Ross, New York University Shanghai, United States

Recent Advances in Sample Efficient DRL

April 15th, 2021

9:00pm – 10:00pm EST

Mengdi Wang, Princeton University, United States

Compressive state representation learning towards small-data RL applications

April 1st, 2021

9:00pm – 10:00pm EST

Wenbin Lu, North Carolina State University, United States

Jump Q-Learning for Optimal Interval-Values Treatment Decision Rule

Discussion Leader: Guanhua, Chen, University of Wisconsin-Madison, United States

March 18th, 2021

8:30pm – 9:30pm EST

Dong Zhang, Western University, Canada

Deep reinforcement learning in medical object detection and segmentation

Discussion Leader: Shuo Li, Western University, Canada

March 4th, 2021

8:00pm – 9:00pm EST

Peng Wei, George Washington University

Deep Multi-Agent Reinforcement Learning for Autonomous Urban Air Mobility

February 18th, 2021

8:00pm – 9:00pm EST

Zhiyuan Liu, Southeast University, Nanjing China

Urban Transport Simulation Using Reinforcement Learning

Discussion Leader: Cheng Lyu, Southeast University, Nanjing China

January 28th, 2021

8:00pm – 9:00pm EST

Yuxi Li, author of the 150 pages Deep Reinforcement Learning: An Overview

Reinforcement Learning Applications

Discussion Leader: Lihang Ying, president of Alberta AI Association

January 14th, 2021

8:00pm – 9:00pm EST

Yanhua Li, Worcester Polytechnic Institute (WPI)

Decision Analysis from Human-Generated Spatial-Temporal Data

Discussion Leader: Haipeng Chen, Harvard University

December 16th, 2020

8:00pm – 9:00pm EST

Liam Paull, l’Université de Montréal

Training Robotics in Simulators

December 3rd, 2020

8:00pm – 9:00pm EST

Nick Rhinehart, University of California, Berkeley

Jointly Forecasting and Controlling Behavior by Learning From High-Dimensional Data

November 19th, 2020

10:00am – 11:00am EST

Nathan Kallus, Cornell University

Statistically Efficient Offline Reinforcement Learning

Discussion Leader: Chengchun Shi, London School of Economics and Political Science

November 5th, 2020

10:00am – 11:00am EST

Eric Laber, NC State University

Partially observable Markov Decision Processes as a Model for Chronic Illness

October 21st, 2020

11:00am – 12:00pm EST

Yansheng Wang, Beihang University & Fanyou Wu, Purdue University

KDD Cup 2020 RL Track Winners Presentation

October 7th, 2020

11:00am – 12:00pm EST

Tony Qin, DiDi AI Labs

Deep Reinforcement Learning in a Ride-sharing Marketplace

September 24th, 2020

11:00am – 12:00pm EST

Michael R. Kosorok, University of North Carolina at Chapel Hill

Off-Policy Reinforcement Learning for Estimation of Optimal Treatment Regime

August 27th, 2020

10:00am – 11:25am EST

Bo An, Nanyang Technological University

Reinforcement Learning in Competitive Environment

Susan Murphy, Harvard University

Intelligent Poolin: Practical Thompson Sampling for mHealth