Weichao Mao (毛威超)

I am a PhD candidate at University of Illinois Urbana–Champaign (UIUC). I am fortunate to be advised by Prof. Tamer Başar at the Coordinated Science Laboratory (CSL).

Before joining UIUC, I got my bachelor's degree of Computer Science from Shanghai Jiao Tong University (SJTU). I was advised by Prof. Fan Wu and Prof. Zhenzhe Zheng at Advanced Network Laboratory (ANL).

My research interests lie in reinforcement learning, game theory, control, and multi-agent systems.

Contact

Email :
Office : 360 CSL, 1308 W Main St, Urbana, IL 61801

Education

University of Illinois at Urbana-Champaign, Urbana, IL
Ph.D. student in Electrical and Computer Engineering, 2019.9 - Present

Shanghai Jiao Tong University, Shanghai, China
B.S. in Computer Science, 2015.9 - 2019.6

Journal Papers

Model-Free Non-Stationary RL: Near-Optimal Regret and Applications in Multi-Agent RL and Inventory Control
Weichao Mao, Kaiqing Zhang, Ruihao Zhu, David Simchi-Levi, and Tamer Başar
Management Science (Accepted), 2023

Provably Efficient Reinforcement Learning in Decentralized General-Sum Markov Games
Weichao Mao, and Tamer Başar
Dynamic Games and Applications, 13(1):165-186, 2023


Conference Papers

\(\widetilde{O}(T^{-1})\) Convergence to (Coarse) Correlated Equilibria in Full-Information General-Sum Markov Games
Weichao Mao, Haoran Qiu, Chen Wang, Hubertus Franke, Zbigniew T Kalbarczyk, and Tamer Başar
In submission

FLASH: Fast Model Adaptation in ML-Centric Cloud Platforms
Haoran Qiu, Weichao Mao, Archit Patke, Shengkun Cui, Chen Wang, Hubertus Franke, Zbigniew T Kalbarczyk, Tamer Başar, and Ravishankar K Iyer
In Proceedings of the 7th Annual Conference on Machine Learning and Systems (MLSys 2024)

Multi-Agent Meta-Reinforcement Learning: Sharper Convergence Rates with Task Similarity
Weichao Mao, Haoran Qiu, Chen Wang, Hubertus Franke, Zbigniew T Kalbarczyk, Ravishankar K Iyer, and Tamer Başar
In Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS 2023)

AWARE: Automate Workload Autoscaling with Reinforcement Learning in Production Cloud Systems
Haoran Qiu, Weichao Mao, Chen Wang, Hubertus Franke, Alaa Youssef, Zbigniew T Kalbarczyk, Tamer Başar, and Ravishankar K Iyer
In Proceedings of the 2023 USENIX Annual Technical Conference (USENIX ATC 2023)

Decentralized Learning of Finite-Memory Policies in Dec-POMDPs
Weichao Mao, Kaiqing Zhang, Zhuoran Yang, and Tamer Başar
In Proceedings of the 22nd IFAC World Congress (IFAC WC 2023)

A Mean-Field Game Approach to Cloud Resource Management with Function Approximation
Weichao Mao, Haoran Qiu, Chen Wang, Hubertus Franke, Zbigniew T Kalbarczyk, Ravishankar K Iyer, and Tamer Başar
In Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

SIMPPO: A Scalable and Incremental Online Learning Framework for Serverless Resource Management
Haoran Qiu, Weichao Mao, Archit Patke, Chen Wang, Hubertus Franke, Zbigniew T Kalbarczyk, Tamer Başar, and Ravishankar K Iyer
In Proceedings of 13th ACM Symposium on Cloud Computing (SoCC 2022)

On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning
Weichao Mao, Lin F. Yang, Kaiqing Zhang, and Tamer Başar
In Proceedings of the 39th International Conference on Machine Learning (ICML 2022)

Near-Optimal Model-Free Reinforcement Learning in Non-Stationary Episodic MDPs
Weichao Mao, Kaiqing Zhang, Ruihao Zhu, David Simchi-Levi, and Tamer Başar
In Proceedings of the 38th International Conference on Machine Learning (ICML 2021)

Semiparametric Information State Embedding for Policy Search under Imperfect Information
Sujay Bhatt, Weichao Mao, Alec Koppel, and Tamer Başar
In Proceedings of the 60th Conference on Decision and Control (CDC 2021)

POLY-HOOT: Monte-Carlo Planning in Continuous Space MDPs with Non-Asymptotic Analysis
Weichao Mao, Kaiqing Zhang, Qiaomin Xie, and Tamer Başar
In Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS 2020)

Information State Embedding in Partially Observable Cooperative Multi-Agent Reinforcement Learning
Weichao Mao, Kaiqing Zhang, Erik Miehling, and Tamer Başar
In Proceedings of the 59th Conference on Decision and Control (CDC 2020)

Pricing for Revenue Maximization in IoT Data Markets: An Information Design Perspective
Weichao Mao, Zhenzhe Zheng, and Fan Wu
In Proceedings of the 38th IEEE International Conference on Computer Communications (INFOCOM 2019)

Endowing Matching Algorithm with Adaptability in Content-based Publish/Subscribe Systems
Shiyou Qian, Weichao Mao, Jian Cao, Frederic Le Mouel, and Minglu Li
In Proceedings of the 38th IEEE International Conference on Computer Communications (INFOCOM 2019)

Workshop Papers

On the Promise and Challenges of Foundation Models for Learning-based Cloud Systems Management
Haoran Qiu, Weichao Mao, Chen Wang, Hubertus Franke, Zbigniew T Kalbarczyk, Tamer Başar, and Ravishankar K Iyer
In Proceedings of the 7th Workshop on Machine Learning for Systems at NeurIPS (ML4Sys@NeurIPS 2023)

Action Dynamics Task Graphs for Learning Plannable Representations of Procedural Tasks
Weichao Mao, Ruta Desai, Michael Louis Iuzzolino, and Nitin Kamra
In AAAI Workshop on User-Centric Artificial Intelligence for Assistance in At-Home Tasks (AI4AtHome 2023)

Reinforcement Learning for Resource Management in Multi-tenant Serverless Platforms
Haoran Qiu, Weichao Mao, Archit Patke, Chen Wang, Hubertus Franke, Zbigniew T Kalbarczyk, Tamer Başar, and Ravishankar K Iyer
In Proceedings of the 2nd European Workshop on Machine Learning and Systems (EuroMLSys 2022)

Teaching

Teaching Assistant for ECE 561: Statistical Inference for Engineers and Data Scientists (Spring 2023), UIUC

Teaching Assistant for CS 499: Mathematical Foundations of Computer Science (Spring 2018), SJTU

Awards

Shun Lien Chuang Memorial Award, UIUC, 2023

Robert T. Chien Memorial Award, UIUC, 2022

Excellent Bachelor Thesis Award (top 1%), SJTU, 2019

Excellent Graduate Award, SJTU, 2019