Szymon Sidor
Papers
1
Total Citations
1,588
H-Index
1
About
Szymon Sidor is a leading researcher in reinforcement learning (RL) and robotics, best known for his groundbreaking work in dexterous manipulation. His most cited paper, "Learning dexterous in-hand manipulation" (2019, 1,588 citations), demonstrates how RL can train policies for complex, vision-based object reorientation on a physical Shadow Dexterous Hand entirely in simulation. By randomizing physical properties during training, Sidor and his team achieved remarkable sim-to-real transfer, enabling a robotic hand to manipulate objects with unprecedented agility. This work represents a major contribution to bridging the gap between simulated training and real-world robotic control, addressing one of the field’s most persistent challenges. Sidor’s research has profoundly impacted the development of general-purpose manipulation skills, inspiring subsequent work in domain randomization and model-free RL for robotics. His achievements highlight the power of scalable simulation-based learning, making him a pivotal figure in advancing autonomous dexterous systems.
Research Focus
Key Achievements
Top Papers
- 1Learning dexterous in-hand manipulation1,588 citations · 2019