Zhaoyang Fu
Papers
1
Total Citations
9
H-Index
1
About
Zhaoyang Fu is a researcher advancing the frontiers of reinforcement learning, with a particular focus on reward design and decision-making systems. Their most cited work, "Automatic Successive Reinforcement Learning with Multiple Auxiliary Rewards" (2019, 9 citations), tackles a critical challenge in the field: how to efficiently guide learning in complex applications like robotics motion, self-driving, and recommendation systems. Fu’s key contribution lies in developing methods to automatically generate and manage multiple auxiliary rewards, enabling more effective and efficient training of reinforcement learning agents. This work addresses the fundamental problem of reward sparsity and shaping, offering a systematic approach to improve learning outcomes without extensive manual engineering. By focusing on the reward function—a crucial component that directly impacts algorithm performance—Fu has provided valuable insights for both theoretical understanding and practical deployment. Their research continues to influence how autonomous systems learn from their environments, making reinforcement learning more accessible and robust for real-world applications. With a growing citation impact, Fu’s work represents an important step toward more intelligent and adaptive decision-making in autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1