UMD papers by Zhang, Manocha groups at ICML 2023

The University of Maryland had a strong showing at the 40^th International Conference on Machine Learning (ICML) 2023, held last month in Honolulu, Hawaii.

Papers by Kaiqing Zhang's group

Revisiting the Linear-Programming Framework for Offline RL with General Function Approximation
Asuman Ozdaglar, Sarath Pattathil, Jiawei Zhang, Kaiqing Zhang (ECE/ISR)

Partially Observable Multi-agent RL with (Quasi-)Efficiency: The Blessing of Information Sharing
Xiangyu Liu, Kaiqing Zhang (ECE/ISR)

Papers by Dinesh Manocha's group

STEERING : Stein Information Directed Exploration for Model-Based Reinforcement Learning
Souradip Chakraborty (UMD), Amrit Bedi (UMD), Alec Koppel, Mengdi Wang, Furong Huang, and ISR-affiliated Dinesh Manocha (ECE/CS/UMIACS)

Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic
Wesley A. Suttle, Amrit Bedi (UMD), Bhrij Patel, Brian Sadler, Alec Koppel, and ISR-affiliated Dinesh Manocha (ECE/CS/UMIACS)

In addition, the conference's Outstanding Paper Award was presented to UMD researchers John Kirchenbauer, Jonas Geiping, Yuxin Wen, Jonathan Katz, Ian Miers, and Tom Goldstein (Katz and Goldstein are affiliated with ECE). Their paper, “A Watermark for Large Language Models,” focuses on embedding watermarks into large language models to help identify the source of specific outputs generated by the model.

Published August 10, 2023