Yingnan Zhao
Papers
1
Total Citations
5
H-Index
1
About
Yingnan Zhao is a rising researcher in artificial intelligence, with a primary focus on reinforcement learning (RL) and reward function design. Their most cited work, "Auxiliary Reward Generation With Transition Distance Representation Learning" (2025, 5 citations), tackles a fundamental challenge in RL: the reliance on human-designed rewards for complex sequential decision-making tasks. Zhao’s key contribution lies in developing a method to automatically generate auxiliary rewards by learning a transition distance representation, which helps agents better understand task progress and improve learning efficiency. This approach reduces the need for extensive manual reward engineering, making RL more practical for real-world applications. Though early in their career, Zhao’s work has already garnered attention for its innovative perspective on reward shaping—a critical area for advancing autonomous systems. Their research bridges the gap between theoretical RL and practical deployment, offering a pathway to more robust and self-supervised learning agents. As the field of AI continues to evolve, Zhao’s contributions to reward generation and representation learning position them as a promising voice in the next generation of reinforcement learning researchers.
Research Focus
Key Achievements
Top Papers
- 1