Technical Program

Note: All times are in Pacific Daylight Time (UTC -7)

C-9: Reinforcement Learning over Networks (invited)

Session Type: Virtual
Time: Tuesday, November 02, 11:15 - 12:45
Location: Room 3
Virtual Session: Attend on Virtual Platform
Session Chairs: Tianyi Chen, Rensselaer Polytechnic Institute, USA and Santiago Paternain, Rensselaer Polytechnic Institute, USA
C-9.1: Multi-Agent Reinforcement Learning in Time-varying Networked Systems
         Yiheng Lin; California Institute of Technology
         Guannan Qu; California Institute of Technology
         Longbo Huang; Tsinghua University
         Adam Wierman; California Institute of Technology
C-9.2: On-policy Reinforcement Learning via Ensemble Gaussian Processes with Application to Resource Allocation
         Konstantinos D. Polyzos; University of Minnesota
         Qin Lu; University of Minnesota
         Alireza Sadeghi; University of Minnesota
         Georgios B. Giannakis; University of Minnesota
C-9.3: Randomized Linear Programming for Tabular Average-Cost Multi-agent Reinforcement Learning
         Alec Koppel; Amazon
         Amrit Bedi; U.S. Army Research Laboratory
         Bhargav Ganguly; Purdue University
         Vaneet Aggarwal; Purdue University
C-9.4: Communication-efficient Offline Policy Optimization from Distributed Batch Data
         Han Shen; Rensselaer polytechnic institute
         Xuefei Li; Rensselaer polytechnic institute
         Songtao Lu; IBM Thomas J. Watson Research Center
         Lior Horesh; IBM Thomas J. Watson Research Center
         Tianyi Chen; Rensselaer polytechnic institute