Reinforcement Learning in Networks and Queues (RLNQ 2021)

Covid information: Under the current circumstances of the COVID-19 pandemic, this workshop will be a fully virtual event as will ACM SIGMETRICS 2021 conference be.

Venue

The workshop will take place on gather.town, in the "Great Wall Room" (top-right of the map). More information on the setup is available on the Sigmetrics website. You should go to the room and press "x". This will re-direct you to the zoom webinar.

Call for Paper

The workshop aims to revisit the development and the application of reinforcement learning techniques in the various application areas covered by the SIGMETRICS conference. Topics include but are not limited to queueing networks (scheduling, resource allocations), cloud computing, cyber-physical systems (including the smart grid), computer and communication networks, etc. This workshop aims to bring together researchers working on the theoretical aspects and the application of reinforcement learning techniques. It is intended to provide a focus on reinforcement learning techniques at SIGMETRICS conferences for talks on early research on the subject. We aim to gather talks based on recent research results (including work in progress or work that have been submitted to a journal) as well as recently published results in other conferences or journals. Thus, part of the goal is to complement and supplement the SIGMETRICS Conference program with such talks without removing any theoretical contributions from the main technical program.

Submissions

We accept two kinds of contributions:

• Abstract (1 or 2pages, single-column)
• Short-papers (3-page short papers, using the standard PER format) Abstracts should contain a link to a full paper (previously published paper or preprint) on which the talk will be based. Unpublished or work-in-progress work should be submitted as short-papers.

Submission are single-blind (i.e. reviewers' identities are kept hidden from authors but authors names are revealed to authors). Link to the submission website.

Important Dates

• May 17: Paper Submission (Hard deadline)
• May 31: Author Notification
• Monday, June 14, 2021: Workshop

Keynote speaker: Jim Dai

Title: Queueing Network Controls via Deep Reinforcement Learning.

Technical Program

All times are EDT.

• 8:55 - 9:00: Introduction
• 9:00 - 10:30: Session 1
• Keynote (9h-10h): Queueing Network Controls via Deep Reinforcement Learning. Jim Dai
• RL-QN: A Reinforcement Learning Framework for Optimal Control of Queueing Systems. Bai Liu, Qiaomin Xie and Eytan Modiano
• Break. 10:40 -- 11:00
• 11:00 - 12:30: Session 2
• Reinforcement Learning for Datacenter Congestion Control. Chen Tessler, Yuval Shpigelman, Gal Dalal, Amit Mandelbaum, Doron Haritan Kazakov, Benjamin Fuhrer, Gal Chechik and Shie Mannor
• Stable Reinforcement Learning with Unbounded State Space. Devavrat Shah, Qiaomin Xie and Zhi Xu
• QWI: Q-learning with Whittle Index. Francisco Robledo, Vivek Borkar, Urtzi Ayesta and Konstantin Avrachenkov.
• Break. 12:30 -- 13:30
• 13:30 - 15:00, Session 3
• Asymptotic Optimality for Decentralised Bandits. Conor Newton, Ayalvadi Ganesh and Henry Reeve
• A Constrained Bandit Approach for Online Dispatching. Xin Liu, Bin Li, Pengyi Shi and Lei Ying
• ORSuite: Benchmarking Suite for Sequential Operations Models Christopher Archer, Siddhartha Banerjee, Mayleen Cortez, Carrie Rucker, Sean Sinclair, Max Solberg, Qiaomin Xie and Christina Yu
• Break. 15:00 -- 15:30
• 15:30 - 17pm, Session 4
• Scalable Reinforcement Learning for Multi-Agent Networked Systems. Guannan Qu, Adam Wierman and Na Li.
• Better than the Best: Gradient-based Improper Reinforcement Learning for Network Scheduling. Mohammani Zaki, Avi Mohan, Aditya Gopalan and Shie Mannor
• Multi-Agent Reinforcement Learning with General Utilities via DecentralizedShadow Reward Actor-Critic. Junyu Zhang, Amrit Bedi, Mengdi Wang and Alec Koppel

Program committee

Workshop chairs:

• Nicolas Gast, Inria
• Neil Walton, University of Manchester.
• Mengdi Wang, Deepmind & Princeton
• Kuang Xu, Stanford

PC members:

• Konstantin Avrachenkov, Inria
• Sid Bannerjee, Cornell
• Sem Borst, TU Eindhoven
• Ana Busic, Inria
• Richard Combes, Supelec
• Quanquan Gu, UCLA
• Niao He, Urbana-Champaign
• Rahul Jain, University of Southern California
• Longbo Huang, Tsinghua University
• Vijay Kamble, University of Illinois
• Gerr Koole, VU Amsterdam
• Siva Maguluri, Georgia Tech
• Eytan Modiano, MIT
• Gergely Neu, Pompeu Fabra
• Sanjay Shakkottai, University of Texas, Austin
• Jinwoo Shin, KAIST
• Adam Weirman, Caltech
• Jiaming Xu, Duke
• Lei Ying, University of Michigan, Ann Arbor
• Zhouran Yang, Princeton