Felix End
Papers
1
Total Citations
11
H-Index
1
About
Felix End is a researcher advancing the frontiers of robot learning through hierarchical reinforcement learning (HRL). His work tackles the fundamental challenge of scaling RL to complex, high-dimensional continuous control tasks—a critical bottleneck for real-world robotics. End’s most cited paper, “Layered Direct Policy Search for Learning Hierarchical Skills” (2017, 11 citations), introduces a novel approach that decomposes complex behaviors into reusable, layered skills. By directly searching over policy parameters in a hierarchical structure, his method enables robots to learn more efficiently and generalize across tasks, overcoming the scalability issues that plague traditional RL. This contribution has helped lay the groundwork for more practical, autonomous robotic systems capable of mastering intricate manipulation and locomotion tasks. End’s research sits at the intersection of reinforcement learning, robotics, and skill acquisition, offering a pathway toward machines that can learn and adapt in the physical world. His work continues to inspire students and researchers seeking to bridge the gap between algorithmic theory and embodied intelligence.
Research Focus
Key Achievements
Top Papers
- 1Layered direct policy search for learning hierarchical skills11 citations · 2017