Keynote Speakers

Zhiwei (Tony) Qin
Principal Scientist at Lyft Rideshare Labs
Title: Reinforcement Learning for Ridesharing: An Overview
Abstract: With the rising prevalence of smart mobile phones in our daily life, online rideshare platforms have emerged as a viable solution to provide more timely and personalized transportation service, led by companies such as Lyft, DiDi, and Uber.  These platforms also allow idle vehicle vacancy to be more effectively utilized to meet the growing need of on-demand transportation, by connecting potential mobility requests to available drivers.  In this talk, we will systematically describe the core operational optimization problems in ridesharing, in particular, order dispatching, driver repositioning, and ride-pooling. Through a tutorial-style format, we will broadly cover reinforcement learning-based methods for solving these problems in the recent literature. We will also discuss the various challenges and potential opportunities on these topics.
Bio: Tony Qin is Principal Scientist at Lyft Rideshare Labs, working on core problems in ridesharing marketplace optimization. Previously, he was Principal Research Scientist and Director of the Decision Intelligence group at DiDi AI Labs and Staff Scientist in supply chain and inventory optimization at Walmart Global E-commerce. Tony received his Ph.D. in Operations Research from Columbia University. His research interests span optimization and machine learning, with a particular focus in reinforcement learning and its applications in operational optimization, digital marketing, and smart transportation. He is Associate Editor of the ACM Journal on Autonomous Transportation Systems. He has published about 40 papers in top-tier conferences and journals in machine learning and optimization and served as Program Committee of NeurIPS, ICML, AAAI, IJCAI, KDD, and a referee of top journals including Transportation Research Part C and Transportation Science.  He and his team received the INFORMS Daniel H. Wagner Prize for Excellence in Operations Research Practice in 2019 and were selected for the NeurIPS 2018 Best Demo Awards.  Tony holds more than 10 US patents in intelligent transportation, supply chain, and recommendation systems.

Cheng Long
Associate Professor at Nanyang Technological University
Title: Pre-Processing and Querying Big Trajectory Data with Reinforcement Learning
Abstract: In a wide range of applications, the traces of moving objects (e.g., taxis and couriers) are tracked by sampling the locations of the objects periodically via devices such as GPS and camera. The resulting data corresponds to a sequence of time-stamped locations and is called trajectory data. The trajectory data is usually pre-processed (e.g., simplified) first and then used for various query processing (e.g., similarity search). Existing exact algorithms for problems of pre-processing and querying trajectory data usually involve some form of enumeration and are computationally expensive while those approximate ones are often based on human-crafted rules and may return solutions of low quality. We observe that many of these problems could be regarded as some sequential decision process, which is to scan the trajectory data sequentially and make decisions along the way. It is well known that reinforcement learning (RL) is a powerful tool for modeling sequential decision processes and has been successful in solving various problems in control, gaming, combinatorial optimization, etc. In this talk, we will first review some background of RL, then present our recent studies of leveraging RL for two problems of pre-processing and querying trajectory data, namely trajectory simplification and sub-trajectory similarity search. The RL-based methods run faster than existing exact algorithms (since they involve no enumeration) and return better solutions than existing approximate algorithms (since they are data-driven and make decisions more intelligently).
Bio: LONG Cheng is currently an Assistant Professor at the School of Computer Science and Engineering (SCSE), Nanyang Technological University (NTU). He got the PhD degree from Hong Kong University of Science and Technology (HKUST) in 2015. His research interests are broadly in data management and data mining. His research has been recognized with one "Best Research Award" provided by ACM-Hong Kong, one "Fulbright-RGC Research Award" provided by Research Grant Council (Hong Kong), two "PG Paper Contest Awards" provided by IEEE-HK, and one "Overseas Research Award" provided by HKUST. He is member of ACM and IEEE.