Yangang Wang

Papers

Total Citations

H-Index

About

Yangang Wang is a researcher at the forefront of applying reinforcement learning to scientific discovery, with a particular focus on bridging artificial intelligence and computational science. His most cited work, "Reinforcement Learning for Scientific Application: A Survey" (2024), provides a comprehensive synthesis of how RL techniques are revolutionizing fields from drug design to materials science, offering a roadmap for integrating machine learning into complex scientific workflows. Though early in its citation trajectory, this survey has already established Wang as a key synthesizer of emerging methodologies. His research contributions center on developing adaptive algorithms that enable autonomous decision-making in experimental and simulation environments, reducing the need for human intervention in iterative scientific processes. Wang’s work is notable for its interdisciplinary approach, combining rigorous theoretical foundations with practical implementations that accelerate hypothesis testing. As a rising voice in the AI-for-science community, he continues to explore how reinforcement learning can optimize resource allocation in high-throughput experiments and improve predictive modeling in data-scarce domains. His scholarship exemplifies the growing synergy between artificial intelligence and traditional scientific inquiry.