Fabian Otto
Papers
1
Total Citations
5
H-Index
1
About
Fabian Otto is a rising researcher in reinforcement learning (RL), with a focus on bridging the gap between black-box optimization and structured control. His most-cited work, "Deep Black-Box Reinforcement Learning with Movement Primitives" (2022), introduces a novel framework that treats RL as an episode-based optimization problem, learning to select controller parameters—represented as movement primitives—for varying task contexts. This approach offers distinct advantages in sample efficiency and robustness, particularly for robotic manipulation and locomotion tasks where smooth, interpretable policies are critical. Otto’s contributions advance the integration of deep learning with traditional control theory, enabling more reliable and data-efficient policy learning. While his citation count is still growing (5 citations for his top paper), his work is gaining traction in the RL community for its practical relevance and theoretical clarity. As a researcher at the intersection of machine learning and robotics, Otto is helping to shape how black-box methods can be effectively applied to real-world control problems, making his research a valuable resource for students and practitioners exploring movement primitives and contextual RL.
Research Focus
Key Achievements
Top Papers
- 1Deep Black-Box Reinforcement Learning with Movement Primitives5 citations · 2022