Conference Paper

• Haitong Ma, Tianpeng Zhang, Yixuan Wu, Flavio P. Calmon, Na Li. Gaussian Max-Value Entropy Search for Multi-Agent Bayesian Optimization. Accepted to IROS 2023. 
  arxiv / Video 

• Dongjie Yu*, Haitong Ma*, Shengbo Eben Li, Jianyu Chen. Reachability Constrained Reinforcement Learning, ICML , 2022. (Dongjie and I contributed equally to this paper)
  arXiv / Publisher's Version / Code / Env 

• Haitong Ma, Chanlgiu Liu, Shengbo Eben Li, Sifa Zheng, Jianyu Chen. Joint Synthesis of Safety Certificate and Safe Control Policy Using Constrained Reinforcement Learning. L4DC, 2022.  (Oral Presentation, Best Paper Award Finalists, 3/176)
  Also presented at Safe Control and Learning under Uncertainty Workshop at MECC 2021.
  arXiv / Publisher's Version / Workshop slides / Video / Talk at L4DC 

• Haitong Ma, Jianyu Chen, Shengbo Eben Li, Ziyu Lin, Yang Guan, Yangang Ren, Sifa Zheng. Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function. IROS, 2021.
  Code

• Yang Guan*, Yangang Ren*, Haitong Ma, Jianyu Chen, Shengbo Eben Li, Qi Sun, Yifan Dai, Bo Cheng. Learn collision-free self-driving skills at urban intersections with model-based reinforcement learning, in IEEE International Intelligent Transportation Systems Conference (ITSC), 2021. (Best Student Paper Award, 2/597)
  Paper / Video

Journal Paper

• Haitong Ma, Chanlgiu Liu, Shengbo Eben Li, Sifa Zheng, Wenchao Sun, Jianyu Chen. Learn Zero-Constraint-Violation Policy in Model-Free Constrained Reinforcement Learning. Accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023. Paper

• Yang Guan*, Yangang Ren*, Qi Sun, Shengbo Eben Li, Haitong Ma, Jingliang Duan, Yifan Dai, Bo Cheng. Integrated Decision and Control: Toward Interpretable and Computationally Efficient Driving Intelligence. IEEE Transactions on Cybernetics, 2022.
  Paper / Video / Code / Project page

Preprints

• Tongzheng Ren*, Zhaolin Ren*, Haitong Ma, Na Li, Bo Dai. Stochastic Nonlinear Control via Finite-dimensional Spectral Dynamic Embedding, 2023. arXiv 
• Haitong Ma, Yang Guan, Shengbo Eben Li, Xiangteng Zhang, Sifa Zheng, Jianyu Chen. Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety. arXiv, 2021.

See my Google Scholar page for a full list of my publications.