Jiancong Huang

Papers

Total Citations

H-Index

About

Jiancong Huang is a researcher specializing in reinforcement learning and robotic control, with a particular focus on improving the efficiency and adaptability of deep reinforcement learning (DRL) systems. His work addresses some of the most pressing challenges in autonomous robot learning, including the optimization of hyperparameters and the reduction of sample requirements — two critical bottlenecks that have long hindered the real-world deployment of learning-based robotic systems. His most cited contribution, "Hyperparameter Auto-Tuning in Self-Supervised Robotic Learning" (2021, 11 citations), tackles the complex problem of hyperparameter selection in policy optimization, demonstrating how poorly chosen parameters can lead to insufficient or redundant learning outcomes. Complementing this, his earlier work "Towards More Sample Efficiency in Reinforcement Learning with Data Augmentation" (2019, 3 citations) introduced novel data augmentation techniques designed to enable DRL agents to learn more from limited observed data — a significant step toward making adaptive robot control practically viable. Together, these contributions reflect Huang's commitment to making reinforcement learning more robust and accessible for real-world robotics applications, offering foundational tools for researchers seeking to build smarter, more data-efficient autonomous systems.