ICON Seminar in Autonomy: Prof. Kaiqing Zhang (University of Maryland)
| Event Date: | September 12, 2025 |
|---|---|
| Speaker: | Prof. Kaiqing Zhang |
| Speaker Affiliation: | University of Maryland |
| Priority: | No |
| College Calendar: | Show |
Time: 3-4 pm Eastern Time, Sep 12 (Friday), 2025
Location: MSEE 112
Zoom Link: https://purdue-edu.zoom.us/j/98798335169
Coffee and snacks will be provide.
Towards Principled AI Agents under Decentralized and Asymmetric Information
Abstract:
AI Models have been increasingly deployed to develop "Autonomous Agents" for decision-making, with prominent application examples including playing Go and video games, robotics, autonomous driving, healthcare, human-assistant, etc. Most such success stories naturally involve multiple AI-agents interacting dynamically with each other and humans. More importantly, these agents oftentimes operate with asymmetric information in practice, both across different agents and across the training-testing phases. In this talk, we will share some of our recent explorations in understanding (multi-)AI-agents' decision-making under such decentralized and asymmetric information. First, we will focus on Reinforcement Learning (RL)-Agents, in partially observable environments: we will analyze the pitfalls and efficiency of RL in partially observable Markov decision processes when there is privileged information in training, a common practice in robot learning and deep RL, and in partially observable stochastic games, when information-sharing is allowed among decentralized agents. We will show the provable benefits of privileged information and information sharing in these cases. Second, we will examine Large-Language-Model (LLM)-(powered-)Agents, which use LLM as the main controller for decision-making, by understanding and enhancing their decision-making capability in canonical decentralized and multi-agent scenarios.
Speaker:
Kaiqing Zhang is an Assistant Professor in Electrical and Computer Engineering and the Institute for Systems Research at the University of Maryland, with joint appointment in Computer Science. He is a member of the Center for Machine Learning, Maryland Robotics Center, and the AI Interdisciplinary Institute. Previously, he was a postdoctoral scholar at MIT (LIDS and CSAIL) and a Research Fellow at the Simons Institute, UC Berkeley. He received his Ph.D. in ECE and M.S. degrees in ECE and Applied Mathematics from UIUC, and a B.E. in Automation and Economics from Tsinghua University. His research spans control and decision theory, game theory, reinforcement learning, robotics, and computation. His work has earned recognition including the Simons-Berkeley Fellowship, ICML Outstanding Paper Award, NSF CAREER, AFOSR YIP, and several research and teaching awards.
Organizers: Ziran Wang (ziran@purdue.edu), Yan Gu (yangu@purdue.edu), Yu She (shey@purdue.edu)
2025-09-12 08:00:00 2025-09-12 17:00:00 America/Indiana/Indianapolis ICON Seminar in Autonomy: Prof. Kaiqing Zhang (University of Maryland) Purdue University