Distributed coordination (Control, optimization, game theory and learning)
News
September 2025: Our paper “Byzantine-resilient federated online learning for Gaussian process regression” will appear in Automatica.
August 2025: Former Ph.D. student Yang Lu joins Nanjing University, China, as Assistant Professor.- July 2025: Our paper “Meta-reinforcement learning with adaptation from human feedback via preference-order-preserving task embedding” appears at ICML 2025.
- June 2025: Our paper “Attack estimation of switched nonlinear control systems using invertibility” will appear in IEEE TCNS.
- May 2025: Our paper “UTILITY: Utilizing explainable reinforcement learning to improve reinforcement learning” appears at ICLR 2025.
April 2025: Zhenyuan Yuan and Siyuan Xu receive the EE Graduate Student Publication Excellence Award.- November 2024: Two papers appear at NeurIPS 2024: “In-trajectory inverse reinforcement learning: Learn incrementally before an ongoing trajectory terminates” and “Meta-reinforcement learning with universal policy adaptation: Provable near-optimality under all-task optimum comparator”.
- August 2024: Former Ph.D. student Samer Saab joins Department of Electrical and Computer Engineering at Lebanese American University, Lebanon, as Assistant Professor.
- July 2024: Our paper “Federated reinforcement learning for robot motion planning with zero-shot generalization” appears in Automatica.
- June 2024: Our paper “Lightweight distributed Gaussian process regression for online machine learning” appears in IEEE TAC.
- May 2024: Our paper “Meta inverse constrained reinforcement learning: Convergence guarantee and generalization analysis” appears at ICLR 2024.
- April 2024: Our paper “Secure perception-driven control of mobile robots using chaotic encryption” appears in IEEE TAC.
- December 2023: Two papers appear at NeurIPS 2023: “Online constrained meta-learning: Provable guarantees for generalization” and “Learning multi-agent behaviors from distributed and streaming demonstrations”.
- July 2023: Former Ph.D. student Guoxiang Zhao joins Institute of Artificial Intelligence at Shanghai University, China as an Associate Professor.
- June 2023: Two papers appear at ACC 2023: “Federated reinforcement learning for generalizable motion planning” and “Multi-robot-assisted human crowd control for emergency evacuation: A stabilization approach”.
- February 2023: Our paper “Efficient gradient approximation method for constrained bilevel optimization” appears at AAAI 2023.
- December 2022: Two papers appear at NeurIPS 2022: “Distributed inverse constrained reinforcement learning for multi-agent systems” and “Byzantine-tolerant federated Gaussian process regression for streaming data”.
- October 2022: Two new journal papers: “A multivariate adaptive gradient algorithm with reduced tuning efforts” appears in Neural Networks and “An adaptive polyak heavy-ball method” appears in Machine Learning.
- August 2022: Former Ph.D. student Hunmin Kim joins Department of Electrical and Computer Engineering at Mercer University as an Assistant Professor.
- July 2022: Our paper “Meta value learning for fast policy-centric optimal motion planning” appears at RSS 2022.
- June 2022: Our paper “Scalable distributed algorithms for multi-robot near-optimal motion planning” appears in Automatica.
- March 2022: Our paper “Distributed economic control of dynamically coupled networks” appears in IEEE Transactions on Cybernetics.
- October 2021: Our paper “A co-design adaptive defense scheme with bounded security damages against Heartbleed-like attacks” appears in IEEE TIFS.
- September 2021: Our paper “Pareto optimal multi-robot motion planning” appears in IEEE TAC.
- April 2021: Zhenyuan Yuan receives the Penn State Alumni Association Scholarship for Penn State Alumni in the Graduate School.
- November 2020: Our paper “Distributed robust adaptive frequency control of power systems with dynamic loads” appears in IEEE TAC.
- July 2020: Our paper “Communication-aware distributed Gaussian process regression algorithms for real-time machine learning” appears at ACC 2020.
- May 2020: Our paper “On privacy preserving data release of linear dynamic networks” appears in Automatica.
- January 2020: Our paper “Simultaneous input and state estimation for stochastic nonlinear systems with additive unknown inputs” appears in Automatica.