Hongqiu Wu

Papers

Total Citations

H-Index

About

Hongqiu Wu is a rising researcher whose work lies at the intersection of reinforcement learning, causal inference, and decision-making under uncertainty. His primary research focus is on building sample-efficient, robust models for action-effect prediction—critical for domains ranging from robot control and recommender systems to personalized medical treatment. In his influential 2022 paper, "Adversarial Counterfactual Environment Model Learning," Wu introduced a novel framework that leverages adversarial training to learn environment models capable of generating counterfactual trajectories. This approach allows agents to simulate unlimited trials without real-world risk, dramatically improving policy learning efficiency and robustness. Although early in his career, Wu’s contributions have already garnered attention, with his work accumulating citations that underscore its growing impact on the reinforcement learning community. By bridging the gap between causal reasoning and model-based RL, Hongqiu Wu is helping to pave the way for safer, more data-efficient autonomous systems.