Rate My Professor Yanqiu Wu

Dr. Yanqiu Wu is a Lecturer in Artificial Intelligence in the School of Computing at Macquarie University, a position she assumed in January 2024. Prior to joining Macquarie, she held the role of CSIRO Early Research Career (CERC) Postdoctoral Research Fellow in the Distributed Systems Security group at Data61, CSIRO, from October 2022 to January 2024. Wu earned her PhD in Computer Science from New York University, awarded on 26 September 2022, with her doctoral research focused on improving sample efficiency in off-policy and offline deep reinforcement learning. She previously received a Bachelor of Science with Honors in Computer Science from New York University Shanghai on 27 May 2017. Her academic journey reflects a strong foundation in computer science, transitioning from undergraduate studies to advanced research in artificial intelligence.

Wu's research specializations include Markov Decision Processes, off-policy and offline Deep Reinforcement Learning, and Quantum Machine Learning, with particular emphasis on Quantum Adversarial Machine Learning. Her expertise areas encompass Artificial Intelligence, Deep Reinforcement Learning, and Quantum Machine Learning. At Macquarie University, she teaches courses such as COMP8221 Advanced Machine Learning, COMP3210 Big Data, PHIL3400 Rights, Responsibilities, and AI, COMP6400 Intelligent Machines, Ethics and Law, and others. She is associated with the Data Horizons Research Centre, Frontier AI Research Centre, and Applied AI Research Centre. Key publications include "Aggressive Q-learning with ensembles: achieving both high sample efficiency and high asymptotic performance" (NeurIPS Deep Reinforcement Learning Workshop, 2022), "Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling" (ICML 2020), "BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning" (NeurIPS 2020), "Quantum-Inspired Machine Learning: a survey" (arXiv, 2023), "Radio signal classification by adversarially robust quantum machine learning" (arXiv, 2023), "Spatio-temporal incentives optimization for ride-hailing services with offline deep reinforcement learning" (arXiv, 2022), and "A survey of progress in LLM alignment from the perspective of reward design" (IEEE Transactions on Artificial Intelligence, 2026). Wu contributes to the academic community through service on the program committee for SecTL 2023 and as a peer reviewer for conferences including ICML 2023, NeurIPS 2022, KDD 2022, and IJCAI.