Joanne Taery Kim

Papers

Total Citations

H-Index

About

Joanne Taery Kim is a rising researcher in robotics and artificial intelligence, whose work focuses on the intersection of deep reinforcement learning (deep RL) and representation learning for robotic systems. Her key contributions lie in understanding how problem formulation—specifically observation spaces—affects the performance and robustness of deep RL algorithms, a critical insight for deploying these methods in real-world tasks. In her highly cited 2021 paper, "Observation Space Matters," she introduced a benchmark and optimization algorithm to address this sensitivity, earning 13 citations and establishing a foundation for more reliable RL applications. Kim also pioneered the use of graph neural networks (GNNs) to learn compact embeddings of robot kinematic structures and motion spaces, as detailed in her 2021 work "Learning Robot Structure and Motion Embeddings using Graph Neural Networks." This approach enables more efficient analysis and control of complex robotic behaviors by capturing the underlying geometric and topological relationships. With a growing citation impact, Kim's research is shaping how robots perceive and interact with their environments, bridging the gap between simulation and practical deployment. Her work is particularly valuable for students and researchers seeking to build more generalizable and robust autonomous systems.