Joo-Seong Heo
Papers
1
Total Citations
25
H-Index
1
About
Dr. Joo-Seong Heo is a leading researcher at the intersection of reinforcement learning (RL) and multi-agent systems, with a focus on bridging the gap between simulated training and real-world deployment. His most cited work, "Federated Reinforcement Learning Acceleration Method for Precise Control of Multiple Devices" (2021, 25 citations), addresses a critical challenge in modern RL: the reality gap that makes it difficult to transfer policies from simulation to physical environments. Heo's key contribution lies in developing a federated learning framework that accelerates RL training while enabling precise, coordinated control of multiple devices—a breakthrough for applications in robotics, autonomous driving, and industrial automation. By distributing learning across devices and aggregating knowledge, his method reduces the overwhelming computational burden of direct real-world RL deployment. This work has garnered attention for its practical approach to scaling RL systems, earning 25 citations and establishing Heo as an innovator in efficient, real-world RL. His research continues to push boundaries in making reinforcement learning more accessible and robust for complex, multi-device environments.
Research Focus
Key Achievements
Top Papers
- 1