Guy Jacob
Papers
1
Total Citations
5
H-Index
1
About
Guy Jacob is a robotics researcher whose work focuses on bridging the critical gap between simulation and real-world robot deployment—a challenge known as sim-to-real transfer. His most influential contribution, "Validate on Sim, Detect on Real – Model Selection for Domain Randomization" (2022), addresses a fundamental bottleneck in domain randomization (DR): how to select the best policy trained in simulation without costly real-world testing. Jacob proposes a practical framework that validates policies in simulation while detecting failures on the real robot, enabling more reliable and efficient model selection. This work has garnered 5 citations and is recognized for its direct impact on making DR-based robot learning more deployable. By tackling the often-overlooked problem of policy selection in randomized environments, Jacob’s research helps accelerate the adoption of simulation-trained policies in real-world robotics applications. His contributions are particularly valuable for students and researchers working on reinforcement learning, robotic manipulation, and sim-to-real transfer, offering a clear, actionable methodology for improving the robustness and trustworthiness of learned robot skills.
Research Focus
Key Achievements
Top Papers
- 1