Lena Schlemmer
Papers
1
Total Citations
8
H-Index
1
About
Lena Schlemmer is a researcher advancing the frontiers of reinforcement learning, with a particular focus on bridging the gap between simulated environments and real-world embodied systems. Her most-cited work, "Sonic to knuckles: Evaluations on transfer reinforcement learning" (2020, 8 citations), tackles a critical challenge in the field: enabling reinforcement learning agents to transfer knowledge from virtual training grounds to physical, embodied platforms. This research addresses the fundamental difficulty of deploying RL in robotics and autonomous systems, where the complexities of real-world interaction—such as sensor noise, mechanical constraints, and unpredictable dynamics—pose significant hurdles. Schlemmer’s contributions lie in systematically evaluating transfer learning techniques, providing insights that help researchers develop more robust and adaptable AI agents. Her work is particularly relevant for students and researchers interested in practical applications of reinforcement learning, from autonomous navigation to robotic manipulation. By focusing on the transfer from simulated to embodied contexts, Schlemmer is helping to pave the way for more reliable and intelligent systems that can learn and adapt in the physical world.
Research Focus
Key Achievements
Top Papers
- 1Sonic to knuckles: Evaluations on transfer reinforcement learning8 citations · 2020