From Statistics to Artificial Intelligence – Reinforcement Learning Conference

Detailed Schedule: www.arlseminar.com/from-statistics-to-artificial-intelligence-reinforcement-learning/

S. Kevin Zhou, University of Science and Technology of China (USTC)

Traits and Trends of AI in Medical Imaging

Andrea Zanette, University of California at Berkeley

Discussant: Xiaocheng Tang, DiDi Labs

Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning

Lerrel Pinto, New York University

Xinrun Wang, Nanyang Technological University, Singapore

Rethinking Representations for Robotics

Bin Dong, Peking University

Xin Wang, Keya Medical

Some Applications of Deep Reinforcement Learning to Imaging and Numerical PDEs

Siwei Lyu, University at Buffalo, State University of New York

Xin Wang, Keya Medical

Image to image transform (I2IT) with deep reinforcement learning

Chengchun Shi, London School of Economics and Political Science

Statistical inference in reinforcement learning

Discussion Leader: Zhengling Qi, George Washington University

Jiayu Zhou, Michigan State University

Advancements in Artificial Intelligence for Neurodegenerative Diseases

Discussion Leader: Fei Wang, Cornell University

Jim Dai, Cornell University & Chinese University of Hong Kong, Shenzhen

Scalable Deep Reinforcement Learning for Ride-Hailing

Linglong Kong, University of Alberta

Damped Anderson Mixing for Deep Reinforcement Learning and Applications

Houssam Nassif, Amazon

Solving Inverse Reinforcement Learning, Bootstrapping Bandits

Zhaoran Wang, Northwestern University

Is Pessimism Provably Efficient for Offline RL?

Zhuoran Yang, Princeton University

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

Guanjie Zheng, Shanghai Jiao Tong University

Improving Urban Traffic Signal Control via Reinforcement Learning

Keith Ross, New York University Shanghai, United States

Recent Advances in Sample Efficient DRL

Mengdi Wang, Princeton University, United States

Compressive state representation learning towards small-data RL applications

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

Dong Zhang, Western University, Canada

Deep reinforcement learning in medical object detection and segmentation

Discussion Leader: Shuo Li, Western University, Canada

Peng Wei, George Washington University

Deep Multi-Agent Reinforcement Learning for Autonomous Urban Air Mobility

Zhiyuan Liu, Southeast University, Nanjing China

Urban Transport Simulation Using Reinforcement Learning

Discussion Leader: Cheng Lyu, Southeast University, Nanjing China

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

Reinforcement Learning Applications

Discussion Leader: Lihang Ying, president of Alberta AI Association

Yanhua Li, Worcester Polytechnic Institute (WPI)

Decision Analysis from Human-Generated Spatial-Temporal Data

Discussion Leader: Haipeng Chen, Harvard University

Liam Paull, l’Université de Montréal

Training Robotics in Simulators

Nick Rhinehart, University of California, Berkeley

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

Nathan Kallus, Cornell University

Statistically Efficient Offline Reinforcement Learning

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

Eric Laber, NC State University

Partially observable Markov Decision Processes as a Model for Chronic Illness

Yansheng Wang, Beihang University & Fanyou Wu, Purdue University

KDD Cup 2020 RL Track Winners Presentation

Tony Qin, DiDi AI Labs

Deep Reinforcement Learning in a Ride-sharing Marketplace

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

Off-Policy Reinforcement Learning for Estimation of Optimal Treatment Regime

Bo An, Nanyang Technological University

Reinforcement Learning in Competitive Environment

Susan Murphy, Harvard University

Intelligent Poolin: Practical Thompson Sampling for mHealth