Katia Sycara

Effective Adaptation in Multi-Agent Teams

Abstract

In this talk, I will discuss the different facets of multi-agent interactions spanning groups consisting only of artificial agents to teams of agents and humans. In agent only teams, an agent can be teacher, student or teammate. In human-agent teams. an agent can be an advisor, observing human teams and providing advice to guide the team to better performance. In this sense, the agent can also be viewed as an enabling coordinator of the human team. An agent can also be a teammate in the human-agent team, where the agent performs part of the teamwork as an equal team member. I will discuss requirements and challenges in each of these configurations, especially in situations where there are multiple humans and multiple agents. I will also present the research work of my group in models of these different multi-agent interactions. The presentation will include our work on: (1) Theory of Mind where an agent learns to infer and predict beliefs, intents and goals of others, (2) explainable action advising where the teacher agent advises student agents while also providing an interpretable explanation that can be reused in future knowledge transfer, (3) neurosymbolic approaches for reasoning and prediction with interpretable concepts, and (4) agent adaptation to new human team mates.

Short bio

Katia Sycara holds the Edward Fredkin Research Chair in Robotics at the School of Computer Science at Carnegie Mellon University (CMU). She is Associate Director for Faculty at the Robotics Institute and affiliated faculty of the departments of Machine Learning, Human Computer Interaction and Language Technologies. She has a B.S in Applied Mathematics from Brown University, M.S. in Electrical Engineering from the University of Wisconsin and PhD in Computer Science from Georgia Institute of Technology. She held the Sixth Century Chair in Computing at the University of Aberdeen, UK and has been awarded a Doctorate Honoris Causa from the University of the Aegean. She is a Fellow of the Institute of Electronic and Electrical Engineers (IEEE), Fellow of the AAAI, the recipient of the ACM/SIGART Agents Research Award and the recipient of the Lifetime Research Award of the Institute of Operations Research and the Management Sciences (INFORMS), Group Decision and Negotiation section. She has received 2 influential 10-year paper awards and multiple best paper awards. She has authored more than 700 technical papers. She is a founding member of the International Foundation of Agents and Multiagent Systems (IFAAMAS), and a founding member of the Semantic Web Science Association. Her research interests are in AI/ML, multi-agent and multi-robot systems and human agent teaming.