Nan Rosemary Ke
Papers
1
Total Citations
5
H-Index
1
About
Nan Rosemary Ke is a leading researcher at the intersection of causality, reinforcement learning, and representation learning. Her work tackles one of AI’s most fundamental challenges: enabling agents to discover causal structures from raw sensory data, rather than relying on pre-defined variables. In her highly influential paper, "Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning," Ke systematically benchmarks how well model-based RL agents can infer causal relationships from visual inputs alone—a critical step toward building robots that truly understand their environments. This work, which has garnered significant attention in the field, bridges the gap between classic causal inference and modern deep learning, offering rigorous evaluation frameworks that have shaped subsequent research. Ke’s contributions are particularly vital for embodied AI, where agents must learn cause-and-effect from pixels without human annotation. Her research continues to push the boundaries of how machines can autonomously discover the underlying structure of the world, making her a key voice in the next generation of intelligent, interpretable AI systems.
Research Focus
Key Achievements
Top Papers
- 1