[ICON Fall25 Seminar] Kaiqing Zhang (UMD) скачать в хорошем качестве

[ICON Fall25 Seminar] Kaiqing Zhang (UMD)

Seminar Information: Date/Time: September 12, Friday, 3 - 4:30 pm, ET Location: MSEE 112 Presenter: Kaiqing Zhang, Assistant Professor, University of Maryland Title: Towards Principled AI Agents under Decentralized and Asymmetric 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. In particular, we use the metric of Regret, commonly studied in Online Learning and RL, to understand LLM-agents’ decision-making limits in context and in controlled experiments. Motivated by the observed pitfalls of existing LLM agents, we also proposed a new fine-tuning loss to promote the no-regret behaviors of the models, both provably and experimentally. Time permitting, we will conclude with some additional thoughts on building principled AI Agents for decision-making with information constraints.