Daoming Lyu

Papers

Total Citations

H-Index

About

Daoming Lyu is a researcher at the forefront of trustworthy and explainable artificial intelligence, with a focused expertise in human-robot interactive decision-making. His work critically addresses the fundamental challenge of building autonomous systems that are not only effective but also transparent and worthy of human trust. Lyu’s major contributions lie in developing frameworks that enhance the interpretability of complex decision-making processes, particularly within reinforcement learning. His most cited paper, "TDM: Trustworthy Decision-Making Via Interpretability Enhancement" (2021), with 21 citations, establishes a foundational approach for ensuring that reliance on autonomy is justified by system comprehension. Further expanding this paradigm, his chapter on "Explainable Neuro-Symbolic Hierarchical Reinforcement Learning" (2021) pioneers the integration of symbolic reasoning with neural networks to create hierarchical models that are inherently more explainable. Through this work, Lyu is shaping a future where intelligent agents can articulate their reasoning, making them safer and more reliable partners in collaborative human-robot environments.