Research

Working Papers

Wang, Q.H., Xu, S.H, Ho, C. P., Petrik, M., Policy Gradient for Robust Markov Decision Processes, available online.
Wang, Q.H., Ruan, H.L., Zhou, S.Y., Chen, Z., Ho, C. P., Risk-Aware Robust Satisficing Markov Decision Processes.
Wang, Q.H., Ho, C. P., Fast Policy Iteration for Singularly Perturbed MDPs.
Yu, Z.D., Wang, Q.H., Chow, A.H.F., Ho, C. P., Skip-stop Bus Scheduling using Robust Markov Decision Processes.

Wang, Q.H., Zha, Y.Q., Ho, C. P., Petrik, M., Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity, accepted in the 42th International Conference on Machine Learning (ICML), 2025.
Wang, Q.H., Ho, C. P., Petrik, M., Policy Gradient in Robust MDPs with Global Convergence Guarantee, accepted in the 40th International Conference on Machine Learning (ICML), 2023.

MSc students at City University of Hong Kong (co-supervised with Dr. Chin Pang Ho):

Qu Tong, Li Jiaxin and Zhang Junjie, “Recommendation System for Creating Courses”, 2021.
Wong Ka Wai, Li Ka Ho, and Choi Sheung Shing, “Recommendation System for Creating Courses”, 2021.

Journal: Machine Learning, Journal of Artificial Intelligence Research, Expert Systems with Applications
Conference: 26th International Conference on Artificial Intelligence and Statistics (AISTATS 2023), 37th Conference on Neural Information Processing Systems (NeurIPS 2023), 12th International Conference on Learning Representations (ICLR 2024), 41st International Conference on Machine Learning (ICML 2024), 39th Conference on Neural Information Processing Systems (NeurIPS 2025),