AI for Social Impact Seminar Series: Long Tran-Thanh

Join Long Tran-Thanh, associate professor at the University of Warwick, for an upcoming talk, "COPs, Bandits, and AI for Good", in the AI for Social Impact Seminar Series.

About the talk

While sequential resource allocation can be often casted as (online) combinatorial optimisation problems (COPs), they can differ from the standard COPs when the decision maker has to perform under uncertainty (e.g., the value of the action is not known in advance, or future events are unknown at the decision-making stage). In the presence of such uncertainty, a popular tool from the decision-making literature, called multi-armed bandits, comes in handy. In this talk, Tran-Thanh will demonstrate how to efficiently combine COPs with bandit models to tackle some AI for Good problems. In particular, he first shows how to combine knapsack models with combinatorial bandits to efficiently allocate firefighting units and drones to mitigate wildfires. He will then demonstrate how interval scheduling, paired up with blocking bandits, can be a useful approach as a housing assignment method for people in need. 

About the speaker

Tran-Thanh is a Hungarian-Vietnamese computer scientist at the University of Warwick, U.K., where he is currently an associate professor. He obtained his doctorate in computer science from Southampton in 2012. Hong has been doing active research in a number of key areas of AI and multi-agent systems, mainly focusing on multi-armed bandits, game theory, and incentive engineering, and their applications to crowdsourcing, human-agent learning, and AI for Good.

He has published more than 60 papers at top AI conferences (AAAI, AAMAS, ECAI, IJCAI, NeurIPS, UAI) and journals (JAAMAS, AIJ), and has received a number of national and international awards. Long currently serves as a board member (2018-2024) of the IFAAMAS Directory Board, the main international governing body of the International Federation for Autonomous Agents and Multiagent Systems. He is also the local chair of the AAMAS 2021 conference.