Speaker: Associate Professor Long Tran-Thanh, University of Warwick, UK (báo cáo trực tiếp)

Talk title: Multiagent learning under strategic behaviours

Time: 15:00 - 16:30, Friday, December 23, 2022.

Seminar: Hybrid seminar (onsite at VIASM and online) [Registration here]

Abstract: Optimisation has been the core of many machine learning (ML) problems. In particular, most of the standard ML techniques can be casted as searching for a minimum (or a maximum) of an objective function (e.g., empirical risk minimisation in offline ML, or regret minimisation in its online counterpart). With the rise of multi-agent learning paradigms, such as federated learning, self-play training (i.e., the agent learns by playing against itself), and multi-agent reinforcement learning, there has been a shift from minimisation problems to minimax optimisation in the recent years.  This shift was mainly influenced by the appearance of generative adversarial networks (GANs), which uses a two-player zero-sum game model to learn the underlying generative model of data (and in which one player aims to minimise an objective function, while the other is trying to counteract, hence the minimax manner). However, the way this minimax problem is solved is still collaborative, as in essence the “opponents” still help each other to converge to a stable solution as fast as possible.

While this collaborative multi-agent learning framework still has its interesting and difficult challenges (existence of convergence, stability, etc), it still cannot capture all the multi-agent learning settings, as it assumes (quasi) full cooperation between agents. In this talk, I will discuss a number of problem settings beyond this collaborative multi-agent learning framework, that allows agents to be selfish or strategic. The common thing in them is that agents don’t have to be fully cooperative anymore, but can follow strategic and selfish behaviours. These problems include: (i) last round/last iterate convergence in non-cooperative multi-agent learning; (ii) efficient learning with limited verifications against strategic manipulators; and (iii) truthful machine learning. Our work has been published at top tier AI/ML conferences such as NeurIPS, AAAI, AAMAS, ALT, and IJCAI. 

Bio: Long Tran-Thanh is an Associate Professor in Artificial Intelligence at the University of Warwick, UK.  Long has been doing active research in a number of key areas of Artificial Intelligence and multi-agent systems, mainly focusing on multi-armed bandits, game theory, and incentive engineering, and their applications to AI for Social Good. He has published more than 80 papers at peer-reviewed A* conferences in AI/ML (including AAAI, AAMAS, CVPR, ECAI, IJCAI, NeurIPS, UAI) and journals (JAAMAS, AIJ), and have received a number of prestigious national/international awards, including 2 best paper honourable mention awards at top-tier AI conferences (AAAI, ECAI), 2 Best PhD Thesis Awards (one in the UK and one in Europe), and the AIJ Prominent Paper Award, for being the author of one of the most influential papers published at the flagship journal in AI. 

Long is currently the Deputy-Head (Director of Research) at the department of Computer Science, University of Warwick. He is also the university’s Research Champion in AI, Data, and Smart Applications theme. In this capacity he is in charge for proposing new research vision and plans for the university’s next 10-year research in AI.

In addition, Long 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, a major sub-field of the AI community. He is also the local chair of AAMAS 2023 (London, UK) and KR 2024 (Hanoi, Vietnam), both are A* international conferences in AI. 

For more information: https://human-agentlearning.github.io/