Yanbo Xue
Papers
1
Total Citations
5
H-Index
1
About
Yanbo Xue’s research lies at the intersection of artificial intelligence, cognitive science, and robotics, with a focus on building machines that learn and reason like humans. Their most-cited work, "Interpretable Reinforcement Learning Inspired by Piaget's Theory of Cognitive Development" (2021), bridges developmental psychology and machine learning by reimagining reinforcement learning through the lens of Piaget’s stages of cognitive growth. This paper, with 5 citations, proposes a framework that not only improves learning efficiency but also enhances interpretability—a critical step toward transparent AI systems. Xue’s contributions challenge conventional deep RL approaches by integrating cognitive theories, offering a path to robots with more human-like intuition and adaptability. Their research addresses fundamental questions about how machines can acquire knowledge through interaction, echoing Skinner’s principles while pushing beyond black-box models. By grounding algorithmic design in established psychological theory, Xue’s work has implications for autonomous systems, educational technology, and human-robot collaboration. Though early in impact, this innovative synthesis of cognition and computation marks Xue as a rising voice in the quest for truly intelligent, interpretable agents.
Research Focus
Key Achievements
Top Papers
- 1