Baicen Xiao
Papers
1
Total Citations
13
H-Index
1
About
Baicen Xiao is a researcher advancing the frontiers of reinforcement learning (RL) and human-AI interaction. His work focuses on making autonomous agents more efficient and intuitive to train, particularly in high-dimensional environments where traditional RL struggles. Xiao’s most cited paper, "FRESH: Interactive Reward Shaping in High-Dimensional State Spaces using Human Feedback" (2020, 13 citations), introduces a novel framework that allows human trainers to provide real-time feedback, effectively shaping an agent’s reward function without requiring expert knowledge. This breakthrough bridges the gap between human intuition and machine learning, enabling faster and more robust policy learning in complex settings like robotics and video games. By demonstrating that non-expert humans can guide agents to achieve higher rewards more efficiently, Xiao’s work has significant implications for accessible AI development and human-in-the-loop systems. His contributions are paving the way for more interactive, transparent, and user-friendly reinforcement learning applications, making him a notable voice in the growing field of human-guided machine intelligence.
Research Focus
Key Achievements
Top Papers
- 1