Publications

You can also find my publications on my Google Scholar profile.

• Hybrid Feedback Sampling for Sample-Efficient Model Predictive Control Chaoyi Pan, Zeji Yi, John Zhang, Zachary Manchester, Guannan Qu, Guanya Shi arXiv:2608.19443, 2026link ControlRoboticsOptimization
• A Theoretical Framework for Parallel Lifelong MAPF Using Group Decentralized Planning Alex DeWeese, Jiaoyang Li, Guannan Qu arXiv:2608.17928, 2026link ★ Highlighted Multi-AgentTheoryReinforcement Learning
• DeltaMomentum: A Key-Value Based Anisotropic Momentum Update via Delta Rule Euijin Hong, Guannan Qu arXiv:2608.19491, 2026link ★ Highlighted LLMOptimization
• Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer Baris Askin, Muhammed Ustaomeroglu, Anupam Nayak, Gauri Joshi, Guannan Qu, Carlee Joe-Wong arXiv:2605.12798, 2026link LLMInterpretability
• Revisiting Policy Gradients for Restricted Policy Classes: Escaping Myopic Local Optima with k-Step Policy Gradients Alex DeWeese, Guannan Qu arXiv:2605.10909, 2026link ★ Highlighted Reinforcement LearningOptimizationTheory
• Towards Effective Theory of LLMs: A Representation Learning Approach Muhammed Ustaomeroglu, Guannan Qu arXiv:2605.09294, 2026linkproject website ★ Highlighted LLMInterpretability
• UAVGENT: A Language-Guided Distributed Control Framework Ziyi Zhang, Xiyu Deng, Guannan Qu, Yorie Nakahira arXiv:2602.13212, 2026link Multi-AgentControlLLM
• BLOCK-EM: Preventing Emergent Misalignment via Latent Blocking Muhammed Ustaomeroglu, Guannan Qu ICML, 2026link LLMInterpretabilityOptimization
• Much Ado About Noising: Dispelling the Myths of Generative Robotic Control Chaoyi Pan, Giri Anantharaman, Nai-Chieh Huang, Claire Jin, Daniel Pfrommer, Chenyang Yuan, Frank Permenter, Guannan Qu, Nicholas Boffi, Guanya Shi, Max Simchowitz ICLR, 2026link ★ Highlighted DiffusionControlRobotics
• Polynomial Convergence of Riemannian Diffusion Models Xingyu Xu, Ziyi Zhang, Yorie Nakahira, Guannan Qu, Yuejie Chi ICLR, 2026link DiffusionTheory
• Internal Planning in Language Models: Characterizing Horizon and Branch Awareness Muhammed Ustaomeroglu, Baris Askin, Gauri Joshi, Carlee Joe-Wong, Guannan Qu ICLR, 2026link ★ Highlighted LLMInterpretability
• Multi-Period Sparse Optimization for Proactive Grid Blackout Diagnosis Qinghua Ma, Reetam Sen Biswas, Denis Osipov, Guannan Qu, Soummya Kar, Shimiao Li Power Systems Computation Conference, 2026link OptimizationPower Systems
• Transformer-Based Scalable Multi-Agent Reinforcement Learning for Networked Systems with Long-Range Interactions Vidur Sinha, Muhammed Ustaomeroglu, Guannan Qu European Control Conference, 2026 Best Student Paper Awardlink ★ Highlighted Reinforcement LearningMulti-AgentControl
• Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing Zeji Yi, Chaoyi Pan, Guanya Shi, Guannan Qu Transactions on Machine Learning Research (TMLR), 2026link OptimizationDiffusionControlTheory
• Whole-Body Model-Predictive Control of Legged Robots with MuJoCo John Z. Zhang, Taylor A. Howell, Zeji Yi, Chaoyi Pan, Guanya Shi, Guannan Qu, Tom Erez, Yuval Tassa, Zachary Manchester ICRA, 2026link ControlRoboticsOptimization
• Natural Policy Gradient for Average Reward Non-Stationary RL Neharika Jali, Eshika Pathak, Pranay Sharma, Guannan Qu, Gauri Joshi Transactions on Machine Learning Research (TMLR), 2026link Reinforcement LearningTheory
• Physics-Informed RL for Real-World HVAC Controls: Lessons from Imitation to Deployment Ozan Baris Mulayim, Guannan Qu, Kevin J. Kircher, Mario Bergés Under review, 2025 Control
• Cyber-Resilient System Identification for Power Grid through Bayesian Integration Shimiao Li, Guannan Qu, Bryan Hooi, Vyas Sekar, Soummya Kar, Larry Pileggi arXiv:2510.14043, 2025link Power Systems
• Thinking Beyond Visibility: A Near-Optimal Policy Framework for Locally Interdependent Multi-Agent MDPs Alex DeWeese, Guannan Qu Under review, 2025link Reinforcement LearningMulti-AgentTheory
• Stabilizing Linear Systems under Partial Observability: Sample Complexity and Fundamental Limits Ziyi Zhang, Yorie Nakahira, Guannan Qu NeurIPS, 2025link ★ Highlighted ControlTheory
• Mean-field Sampling for Cooperative Multi-Agent Reinforcement Learning Emile Anand, Ishani Karmarkar, Guannan Qu NeurIPS, 2025 Spotlightlink Reinforcement LearningMulti-AgentTheory
• A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization Muhammed Ustaomeroglu, Guannan Qu ICML, 2025link LLMTheory
• Fast Bandit-based Policy Adaptation in Diverse Environments Ziyi Zhang, Guannan Qu, Yorie Nakahira ACC, 2025link Reinforcement Learning
• ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills Tairan He, Jiawei Gao, Wenli Xiao, Yuanhang Zhang, Zi Wang, Jiashun Wang, Zhengyi Luo, Guanqi He, Nikhil Sobanbab, Chaoyi Pan, Zeji Yi, Guannan Qu, Kris Kitani, Jessica Hodgins, Linxi Fan, Yuke Zhu, Changliu Liu, Guanya Shi RSS, 2025link Robotics
• Learning to Stabilize LTI Systems on a Single Trajectory under Stochastic Noise Ziyi Zhang, Yorie Nakahira, Guannan Qu UAI, 2025link ControlTheory
• Full-order Sampling-Based MPC for Torque-Level Locomotion Control via Diffusion-Style Annealing Haoru Xue, Chaoyi Pan, Zeji Yi, Guannan Qu, Guanya Shi ICRA, 2025 Best Conference Paper Award Finalistlink ★ Highlighted DiffusionControlRobotics
• Predictive Control and Regret Analysis of Non-Stationary MDP with Look-ahead Information Ziyi Zhang, Yorie Nakahira, Guannan Qu TMLR, 2025link Reinforcement LearningTheory
• Model-based Diffusion for Trajectory Optimization Chaoyi Pan, Zeji Yi, Guanya Shi, Guannan Qu NeurIPS, 2024link ★ Highlighted DiffusionOptimizationControlRobotics
• Locally Interdependent Multi-Agent MDP: Theoretical Framework for Decentralized Agents with Dynamic Dependencies Alex DeWeese, Guannan Qu ICML, 2024link ★ Highlighted Reinforcement LearningMulti-AgentTheory
• Efficient Reinforcement Learning for Routing Jobs in Heterogeneous Queueing Systems Neharika Jali, Guannan Qu, Weina Wang, Gauri Joshi AISTATS, 2024link Reinforcement Learning
• Stability and Regret Bounds on Distributed Truncated Predictive Control for Networked Dynamical Systems Eric Xu, Guannan Qu ACC, 2024link Multi-AgentControlTheory
• Decentralized Graph-Based Multi-Agent Reinforcement Learning Using Reward Machines Jueming Hu, Zhe Xu, Weichang Wang, Guannan Qu, Yutian Pang, Yongming Liu Neurocomputing, 2024link Reinforcement LearningMulti-Agent
• CoVO-MPC: Theoretical Analysis of Sampling-based MPC and Optimal Covariance Design Zeji Yi, Chaoyi Pan, Guanqi He, Guannan Qu, Guanya Shi L4DC, 2024link ControlOptimizationTheory
• Combining Model-based Controller and ML Advice via Convex Reparameterization Junxuan Shen, Adam Wierman, Guannan Qu L4DC, 2024link ControlOptimization
• Stability Constrained Reinforcement Learning for Decentralized Real-Time Voltage Control Jie Feng, Yuanyuan Shi, Guannan Qu, Steven H. Low, Anima Anandkumar, Adam Wierman IEEE Transactions on Control of Network Systems, 2023link Reinforcement LearningMulti-AgentControlPower Systems
• KCRL: Krasovskii-Constrained Reinforcement Learning with Guaranteed Stability in Nonlinear Discrete-Time Systems Sahin Lale, Yuanyuan Shi, Guannan Qu, Kamyar Azizzadenesheli, Adam Wierman, Anima Anandkumar CDC, 2023link Reinforcement LearningControl
• Natural Policy Gradient Preserves Spatial Decay Properties for Control of Networked Dynamical Systems Eric Xu, Guannan Qu CDC, 2023link Multi-AgentControlTheory
• Near-Optimal Distributed Linear-Quadratic Regulator for Networked Systems Sungho Shin, Yiheng Lin, Guannan Qu, Adam Wierman, Mihai Anitescu SIAM Journal on Control and Optimization, 2023link Multi-AgentControlTheory
• Certifying Black-Box Policies with Stability for Nonlinear Control Tongxin Li, Ruixiao Yang, Guannan Qu, Yiheng Lin, Adam Wierman, Steven Low IEEE Open Journal of Control Systems, 2023link Control
• Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning Yizhou Zhang*, Guannan Qu*, Pan Xu*, Yiheng Lin, Zaiwei Chen, Adam Wierman ACM SIGMETRICS, 2023. (Equal contribution)link Reinforcement LearningMulti-AgentTheory
• Compositional Neural Certificates for Networked Dynamical Systems Songyuan Zhang, Yumeng Xiu, Guannan Qu, Chuchu Fan L4DC, 2023 Oral Presentationlink ControlMulti-Agent
• A Scalable Network-Aware Multi-Agent Reinforcement Learning Framework for Decentralized Inverter-based Voltage Control Han Xu, Jialin Zheng, Guannan Qu 2023arXiv:2312.04371link Reinforcement LearningMulti-AgentControlPower Systems
• On the Sample Complexity of Stabilizing LTI Systems on a Single Trajectory Yang Hu, Adam Wierman, Guannan Qu NeurIPS, 2022link ControlTheory
• Bounded-Regret MPC via Perturbation Analysis: Prediction Error, Constraints, and Nonlinearity Yiheng Lin, Yang Hu, Guannan Qu, Tongxin Li, Adam Wierman NeurIPS, 2022link ControlTheory
• Stability Constrained Reinforcement Learning for Real-Time Voltage Control Yuanyuan Shi*, Guannan Qu*, Steven Low, Anima Anandkumar, Adam Wierman ACC, 2022. (Equal contribution)link Reinforcement LearningControlPower Systems
• Robustness and Consistency in Linear Quadratic Control with Predictions Tongxin Li, Ruixiao Yang, Guannan Qu, Guanya Shi, Chenkai Yu, Adam Wierman, Steven Low ACM SIGMETRICS, 2022link ControlTheory
• Decentralized Online Convex Optimization in Networked Systems Yiheng Lin, Judy Gan, Guannan Qu, Yash Kanoria, Adam Wierman ICML, 2022link Multi-AgentOptimizationTheory
• Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges Xin Chen, Guannan Qu, Yujie Tang, Steven Low, Na Li IEEE Transactions on Smart Grid, 2022 Top 5 Papers Awardlink Reinforcement LearningPower Systems
• Scalable Reinforcement Learning of Multi-Agent Networked Systems Guannan Qu, Adam Wierman, Na Li Operations Research, 2022link ★ Highlighted Reinforcement LearningMulti-AgentTheory
• Perturbation-based Regret Analysis of Predictive Control in Linear Time Varying Systems Yiheng Lin*, Yang Hu*, Haoyuan Sun*, Guanya Shi*, Guannan Qu*, Adam Wierman NeurIPS, 2021. (Equal contribution) Spotlightlink ControlTheory
• Multi-agent Reinforcement Learning in Stochastic Networked Systems Yiheng Lin, Guannan Qu, Longbo Huang, Adam Wierman NeurIPS, 2021link Reinforcement LearningMulti-AgentTheory
• Distributed Voltage Control for Three-Phase Unbalanced Distribution Systems with DERs and Practical Constraints Niloy Patari, Anurag K. Srivastava, Guannan Qu, Na Li IEEE Transactions on Industry Applications, 2021link Multi-AgentControlPower Systems
• Online Optimization with Predictions and Switching Costs: Fast Algorithms and the Fundamental Limit Yingying Li, Guannan Qu, Na Li IEEE Transactions on Automatic Control, 2021link ControlOptimizationTheory
• Exploiting Linear Models for Model-Free Nonlinear Control: A Provably Convergent Policy Gradient Approach Guannan Qu, Chenkai Yu, Steven Low, Adam Wierman CDC, 2021link Reinforcement LearningControlTheory
• Stable Online Control of Linear Time-Varying Systems Guannan Qu*, Yuanyuan Shi*, Sahin Lale*, Anima Anandkumar, Adam Wierman L4DC, 2021. (Equal contribution)link Control
• Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward Guannan Qu, Yiheng Lin, Adam Wierman, Na Li NeurIPS, 2020link Reinforcement LearningMulti-AgentTheory
• Semi-Global Exponential Stability of Primal-Dual Gradient Dynamics for Constrained Convex Optimization Yujie Tang, Guannan Qu, Na Li Systems & Control Letters, 2020link ControlOptimizationTheory
• Distributed Optimal Voltage Control with Asynchronous and Delayed Communication Sindri Magnússon, Guannan Qu, Na Li IEEE Transactions on Smart Grid, 2020link Multi-AgentControlPower SystemsTheory
• Accelerated Distributed Nesterov Gradient Descent Guannan Qu, Na Li IEEE Transactions on Automatic Control, 2020link ★ Highlighted Multi-AgentControlOptimizationTheory
• Optimal Distributed Feedback Voltage Control under Limited Reactive Power Guannan Qu, Na Li IEEE Transactions on Power Systems, 2020link Multi-AgentControlPower SystemsTheory
• Learning Optimal Power Flow: Worst-Case Guarantees for Neural Networks Andreas Venzke, Guannan Qu, Steven Low, Spyros Chatzivasileiadis SmartGridComm, 2020 Best Student Paper Awardlink Power Systems
• Scalable Reinforcement Learning of Localized Policies for Multi-Agent Networked Systems Guannan Qu, Adam Wierman, Na Li L4DC, 2020 Oral Presentation, Top 10%link Reinforcement LearningMulti-AgentTheory
• Finite-Time Analysis of Asynchronous Stochastic Approximation and Q-learning Guannan Qu, Adam Wierman COLT, 2020link Reinforcement LearningTheory
• Distributed Optimal Voltage Control for Three Phase Unbalanced Distribution Systems with DERs Niloy Patari, Anurag Srivastava, Guannan Qu, Na Li IEEE Industry Applications Annual Meeting, 2020link Multi-AgentControlPower Systems
• Voltage Control Using Limited Communication Sindri Magnússon, Guannan Qu, Carlo Fischione, Na Li IEEE Transactions on Control of Network Systems, 2019link ControlPower Systems
• Exploiting Fast Decaying and Locality in Multi-Agent MDP with Tree Dependence Structure Guannan Qu, Na Li CDC, 2019link Reinforcement LearningMulti-AgentTheory
• Distributed Greedy Algorithm for Multi-Agent Task Assignment Problem with Submodular Utility Functions Guannan Qu, David Brown, Na Li Automatica, 2019link Multi-AgentOptimizationTheory
• On the Exponential Stability of Primal-Dual Gradient Dynamics Guannan Qu, Na Li IEEE Control Systems Letters, 2019link ControlOptimizationTheory
• Optimal Scheduling of Battery Charging Station Serving Electric Vehicles Based on Battery Swapping Xiaoqi Tan, Guannan Qu, Bo Sun, Na Li, Danny H.K. Tsang IEEE Transactions on Smart Grid, 2019link Power Systems
• Online Markov Decision Processes with Time-Varying Transition Probabilities and Rewards Yingying Li, Aoxiao Zhong, Guannan Qu, Na Li ICML Real-World Sequential Decision Making Workshop, 2019 Reinforcement LearningTheory
• Harnessing Smoothness to Accelerate Distributed Optimization Guannan Qu, Na Li IEEE Transactions on Control of Network Systems, 2018link ★ Highlighted Multi-AgentControlOptimizationTheory
• Using Predictions in Online Optimization with Switching Costs: Algorithms and Fundamental Limits Yingying Li, Guannan Qu, Na Li ACC, 2018link OptimizationTheory
• An Optimal and Distributed Feedback Voltage Control under Limited Reactive Power Guannan Qu, Na Li Power Systems Computation Conference, 2018link Multi-AgentControlPower SystemsTheory
• Accelerated Distributed Nesterov Gradient Descent for Smooth and Convex Functions Guannan Qu, Na Li CDC, 2017link Multi-AgentOptimizationTheory
• Harnessing Smoothness to Accelerate Distributed Optimization Guannan Qu, Na Li CDC, 2016link Multi-AgentOptimizationTheory
• Accelerated Distributed Nesterov Gradient Descent for Smooth and Strongly Convex Functions Guannan Qu, Na Li Allerton Conference, 2016link Multi-AgentOptimizationTheory
• Real-time Decentralized and Robust Voltage Control in Distribution Networks Guannan Qu, Na Li, Munther Dahleh 2016arXiv:1606.08101link Multi-AgentControlPower SystemsTheory
• Distributed Greedy Algorithm for Satellite Assignment Problem with Submodular Utility Function Guannan Qu, David Brown, Na Li IFAC Workshop on Estimation and Control of Networked Systems, 2015link Multi-AgentControlOptimizationTheory
• Real-time Decentralized Voltage Control in Distribution Networks Na Li, Guannan Qu, Munther Dahleh Allerton Conference, 2014link Multi-AgentControlPower Systems

No papers match the current filters.