Jiangshan Hao

Papers

Total Citations

H-Index

About

Jiangshan Hao is a rising researcher at the intersection of robotics, reinforcement learning, and human-robot interaction. His work focuses on solving the critical challenge of enabling robots to learn complex behaviors without manually engineered reward functions. Hao’s major contributions center on advancing imitation learning by integrating human feedback directly into the learning loop. In his highly cited 2023 paper, “GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback,” he proposed a novel framework that combines generative adversarial imitation learning (GAIL) with interactive human evaluation, allowing robots to not only mimic expert trajectories but also improve beyond them through real-time human guidance. His follow-up work, “Model-based Adversarial Imitation Learning from Demonstrations and Human Reward,” extends this paradigm by incorporating model-based RL, significantly improving sample efficiency for high-dimensional robotic control tasks. Though early in his career, Hao’s work has already garnered over 16 citations, demonstrating its growing influence in the field. His research promises to make robot learning more practical, data-efficient, and aligned with human intent, paving the way for safer and more adaptable autonomous systems.