[AI Seminar Series] Seminar by Prof. Zhe Xu, Friday May 15th, 12-1pm, MRB Seminar Room

[Vassilis Tsotras]

The next AI Seminar will be on Friday May 15th, 12-1pm, in the MRB Seminar
Room (1st floor).

*** Pizza and refreshments will be provided ****

To keep track of the number of attendees, please *register* at:
https://www.eventbrite.com/e/ai-seminar-series-tickets-1989124134833

The talk will be given by *Prof. Zhe Xu*, Arizona State University

TITLE: Integrating Logic and Causal Reasoning for Learning and Control in
Autonomous Systems

ABSTRACT:
Artificial intelligence, powered by data-driven methods, has surpassed
human-level performance in many tasks. Yet deploying AI in autonomous
systems remains fundamentally challenging due to limited interpretability,
high data demands, and insufficient logical and causal reasoning in
decision-making. To address these challenges, this talk presents
interpretable and data-efficient learning approaches that integrate
theories and techniques from machine learning, formal methods, and control
theory. Unlike traditional learning approaches, these methods enable agents
to reason over their learning processes, coordinate effectively with other
agents, efficiently enhance operational capabilities to complete complex
tasks in the presence of competitors or adversaries, and swiftly adapt to
novel tasks and environments.

The first part of the talk focuses on learning high-level logical and
causal knowledge from data and its application to physical systems. I
present state-of-the-art methods for learning temporal logic (TL) formulas
and TL-based causal diagrams directly from data.The second part addresses
improving the sample efficiency of reinforcement learning (RL) using
high-level knowledge. I introduce a neuro-symbolic RL framework based on
offline training followed by online fine-tuning, which enables an agent to
reason about its exploration process and distill high-level knowledge from
both offline datasets and online interactions to guide future exploration.
I also present approaches that leverage large language models and
counterfactual reasoning to further accelerate RL. The final part of the
talk focuses on learning and control in multi-agent systems operating in
cooperative, non-cooperative, and incomplete-information stochastic games,
where logical and causal knowledge is discovered in a distributed manner.


Bio:

Zhe Xu is an Assistant Professor in the School for Engineering of Matter,
Transport, and Energy at Arizona State University. Prior to joining ASU, he
was a postdoctoral researcher at the Oden Institute for Computational
Engineering and Sciences at The University of Texas at Austin. He received
his Ph.D. in Electrical Engineering from Rensselaer Polytechnic Institute
in 2018. Dr. Xu is a recipient of the NSF CAREER Award, the Howard Kaufman
’62 Memorial Fellowship, and the ASU Fulton Schools of Engineering Teaching
Recognition Awards (2023–2025). His research interests include formal
methods, autonomous systems, control systems, and reinforcement learning.
He has developed learning, control, and verification methods with
applications in robotics, power systems, smart buildings, and biological
systems.
------------------------------------
Sponsored by the RAISE at UCR Institute, the AI Seminar Series presents
speakers working on cutting edge Foundational AI or applying AI in their
research. The goal of these seminars is to inform the UCR community about
current trends in AI research and promote collaborations between faculty in
this emerging field. These seminars are open to interested faculty and
graduate/undergraduate students. Please forward this email to other
colleagues or students in your lab that may be interested. After the seminar a
discussion will follow for questions, open problems, ideas for possible
collaborations etc.

Sincerely,
Vassilis Tsotras
Professor, CSE Department
co-Director, RAISE at UCR Institute

Amit Roy-Chowdhury
Professor, ECE Department
co-Director, RAISE at UCR Institute
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.ucr.edu/pipermail/raise-seminar/attachments/20260509/30feed8d/attachment.htm>