Zhaolin Ren

Zhaolin Ren
Zhaolin's Quick Links

  • Biography

    Zhaolin's doctoral research focused on developing principled and sample-efficient methods for learning, optimization, and control in real-world physical systems. Before his Ph.D., he completed a B.S. in Mathematics and an M.S. in Statistics at Stanford University. At MERL, Zhaolin is interested in developing sample- efficient optimization and learning methods for system design and control.

  • MERL Publications

    •  Ma, H., Dai, B., Ren, Z., Wang, Y., Li, N., "Offline Imitation Learning upon Arbitrary Demonstrations by Pre-Training Dynamics Representations", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 2025.
      BibTeX TR2025-147 PDF
      • @inproceedings{Ma2025oct,
      • author = {Ma, Haitong and Dai, Bo and Ren, Zhaolin and Wang, Yebin and Li, Na},
      • title = {{Offline Imitation Learning upon Arbitrary Demonstrations by Pre-Training Dynamics Representations}},
      • booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
      • year = 2025,
      • month = oct,
      • url = {https://www.merl.com/publications/TR2025-147}
      • }

  • Other Publications

    •  Xin Chen and Zhaolin Ren, "Regression-Based Single-Point Zeroth-Order Optimization", arXiv preprint arXiv:2507.04223, 2025.
      BibTeX
      • @Article{chen2025regression,
      • author = {Chen, Xin and Ren, Zhaolin},
      • title = {Regression-Based Single-Point Zeroth-Order Optimization},
      • journal = {arXiv preprint arXiv:2507.04223},
      • year = 2025
      • }
    •  Zhaolin Ren, Runyu Zhang, Bo Dai and Na Li, "Scalable Spectral Representations for Multi-Agent Reinforcement Learning in Network MDPs", Proceedings of the 28th International Conference on Artificial Intelligence and Statistics (AISTATS), 2025.
      BibTeX External
      • @Inproceedings{ren2025scalable,
      • author = {Ren, Zhaolin and Zhang, Runyu and Dai, Bo and Li, Na},
      • title = {Scalable Spectral Representations for Multi-Agent Reinforcement Learning in Network {MDP}s},
      • booktitle = {Proceedings of the 28th International Conference on Artificial Intelligence and Statistics (AISTATS)},
      • year = 2025,
      • series = {Proceedings of Machine Learning Research},
      • publisher = {PMLR},
      • url = {https://arxiv.org/abs/2410.17221}
      • }
    •  Zhaolin Ren, Tongzheng Ren, Haitong Ma, Na Li and Bo Dai, "Stochastic Nonlinear Control Via Finite-Dimensional Spectral Dynamics Embedding", IEEE Transactions on Automatic Control, 2025.
      BibTeX
      • @Article{ren2025stochastic,
      • author = {Ren, Zhaolin and Ren, Tongzheng and Ma, Haitong and Li, Na and Dai, Bo},
      • title = {Stochastic Nonlinear Control Via Finite-Dimensional Spectral Dynamics Embedding},
      • journal = {IEEE Transactions on Automatic Control},
      • year = 2025,
      • publisher = {IEEE}
      • }
    •  Zhaolin Ren and Na Li, "TS-RSR: A provably efficient approach for batch Bayesian optimization", SIAM Journal on Optimization, Vol. 35, No. 3, pp. 2155-2181, 2025.
      BibTeX
      • @Article{ren2025ts,
      • author = {Ren, Zhaolin and Li, Na},
      • title = {TS-RSR: A provably efficient approach for batch Bayesian optimization},
      • journal = {SIAM Journal on Optimization},
      • year = 2025,
      • volume = 35,
      • number = 3,
      • pages = {2155--2181},
      • publisher = {SIAM}
      • }
    •  Saba Zerefa, Zhaolin Ren, Haitong Ma and Na Li, "Distributed Thompson sampling under constrained communication", IEEE Control Systems Letters, 2025.
      BibTeX
      • @Article{zerefa2025distributed,
      • author = {Zerefa, Saba and Ren, Zhaolin and Ma, Haitong and Li, Na},
      • title = {Distributed Thompson sampling under constrained communication},
      • journal = {IEEE Control Systems Letters},
      • year = 2025,
      • publisher = {IEEE}
      • }
    •  Shen Li, Yuyang Zhang, Zhaolin Ren, Claire Liang, Na Li and Julie A Shah, "Enhancing preference-based linear bandits via human response time", Advances in Neural Information Processing Systems, Vol. 37, pp. 16852-16893, 2024.
      BibTeX
      • @Article{li2024enhancing,
      • author = {Li, Shen and Zhang, Yuyang and Ren, Zhaolin and Liang, Claire and Li, Na and Shah, Julie A},
      • title = {Enhancing preference-based linear bandits via human response time},
      • journal = {Advances in Neural Information Processing Systems},
      • year = 2024,
      • volume = 37,
      • pages = {16852--16893}
      • }
    •  Haitong Ma, Zhaolin Ren, Bo Dai and Na Li, "Skill transfer and discovery for sim-to-real learning: A representation-based viewpoint", 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024, pp. 8603-8609.
      BibTeX
      • @Inproceedings{ma2024skill,
      • author = {Ma, Haitong and Ren, Zhaolin and Dai, Bo and Li, Na},
      • title = {Skill transfer and discovery for sim-to-real learning: A representation-based viewpoint},
      • booktitle = {2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
      • year = 2024,
      • pages = {8603--8609},
      • organization = {IEEE}
      • }
    •  Runyu Zhang, Zhaolin Ren and Na Li, "Gradient play in stochastic games: stationary points, convergence, and sample complexity", IEEE Transactions on Automatic Control, Vol. 69, No. 10, pp. 6499-6514, 2024.
      BibTeX
      • @Article{zhang2024gradient,
      • author = {Zhang, Runyu and Ren, Zhaolin and Li, Na},
      • title = {Gradient play in stochastic games: stationary points, convergence, and sample complexity},
      • journal = {IEEE Transactions on Automatic Control},
      • year = 2024,
      • volume = 69,
      • number = 10,
      • pages = {6499--6514},
      • publisher = {IEEE}
      • }
    •  Zhaolin Ren, Yang Zheng, Maryam Fazel and Na Li, "On controller reduction in Linear Quadratic Gaussian Control with performance bounds", Learning for Dynamics and Control Conference, 2023, pp. 1008-1019.
      BibTeX
      • @Inproceedings{ren2023controller,
      • author = {Ren, Zhaolin and Zheng, Yang and Fazel, Maryam and Li, Na},
      • title = {On controller reduction in Linear Quadratic Gaussian Control with performance bounds},
      • booktitle = {Learning for Dynamics and Control Conference},
      • year = 2023,
      • pages = {1008--1019},
      • organization = {PMLR}
      • }
    •  Zhaolin Ren, Yujie Tang and Na Li, "Escaping saddle points in zeroth-order optimization: the power of two-point estimators", International Conference on Machine Learning, 2023, pp. 28914-28975.
      BibTeX
      • @Inproceedings{ren2023escaping,
      • author = {Ren, Zhaolin and Tang, Yujie and Li, Na},
      • title = {Escaping saddle points in zeroth-order optimization: the power of two-point estimators},
      • booktitle = {International Conference on Machine Learning},
      • year = 2023,
      • pages = {28914--28975},
      • organization = {PMLR}
      • }
    •  Yujie Tang, Zhaolin Ren and Na Li, "Zeroth-order feedback optimization for cooperative multi-agent systems", Automatica, Vol. 148, pp. 110741, 2023.
      BibTeX
      • @Article{tang2023zeroth,
      • author = {Tang, Yujie and Ren, Zhaolin and Li, Na},
      • title = {Zeroth-order feedback optimization for cooperative multi-agent systems},
      • journal = {Automatica},
      • year = 2023,
      • volume = 148,
      • pages = 110741,
      • publisher = {Elsevier}
      • }
    •  Aoxiao Zhong, Hao He, Zhaolin Ren, Na Li and Quanzheng Li, "FedDAR: Federated Domain-Aware Representation Learning", International Conference on Learning Representations (ICLR), 2023.
      BibTeX External
      • @Inproceedings{zhong2023feddar,
      • author = {Zhong, Aoxiao and He, Hao and Ren, Zhaolin and Li, Na and Li, Quanzheng},
      • title = {{FedDAR}: Federated Domain-Aware Representation Learning},
      • booktitle = {International Conference on Learning Representations (ICLR)},
      • year = 2023,
      • note = {Preprint: arXiv:2209.04007},
      • url = {https://arxiv.org/abs/2209.04007}
      • }
    •  Zhaolin Ren, Aoxiao Zhong and Na Li, "LQR with tracking: A zeroth-order approach and its global convergence", 2021 American Control Conference (ACC), 2021, pp. 2562-2568.
      BibTeX
      • @Inproceedings{ren2021lqr,
      • author = {Ren, Zhaolin and Zhong, Aoxiao and Li, Na},
      • title = {LQR with tracking: A zeroth-order approach and its global convergence},
      • booktitle = {2021 American Control Conference (ACC)},
      • year = 2021,
      • pages = {2562--2568},
      • organization = {IEEE}
      • }