Zhaoyang Yang

About

Zhaoyang Yang is a leading researcher in artificial intelligence, specializing in deep reinforcement learning for robotic control. His work addresses the fundamental challenge of enabling machines to master complex, continuous-action tasks—a critical step toward autonomous systems. Yang’s most influential contribution is his 2018 paper, "Hierarchical Deep Reinforcement Learning for Continuous Action Control," which has garnered 197 citations. In this work, he introduced a novel hierarchical algorithm that allows robots to learn both basic and compound skills simultaneously, solving long-standing issues in multi-step robotic manipulation. Building on this, his 2017 paper on multi-task learning demonstrated how a single network can efficiently handle multiple tasks, reducing parameter requirements by over 75% per task compared to traditional methods. This breakthrough significantly improves scalability and computational efficiency in AI training. With 59 citations, this work underscores Yang’s impact on making reinforcement learning more practical for real-world applications. His research has profound implications for robotics, autonomous driving, and industrial automation, cementing his reputation as a pioneer in continuous control and hierarchical learning.

Research Focus

Key Achievements

Top Papers

1. 1
   Hierarchical Deep Reinforcement Learning for Continuous Action Control

   197 citations · 2018
2. 2
   Multi-Task Deep Reinforcement Learning for Continuous Action Control

   59 citations · 2017

Key Collaborators

Contact & Links