Deniz Ergene
Papers
1
Total Citations
10
H-Index
1
About
Deniz Ergene is a researcher at the forefront of bridging the gap between simulated and real-world robotics through advanced reinforcement learning. Their primary focus lies in domain adaptation for robotic systems, specifically addressing the critical challenge of transferring policies trained in simulation to physical platforms—a problem known as the "sim-to-real" gap. Ergene’s most cited work, "Fine-tuning Deep Reinforcement Learning Policies with r-STDP for Domain Adaptation" (2022, 10 citations), introduces a novel approach that leverages reward-modulated spike-timing-dependent plasticity (r-STDP) to fine-tune deep reinforcement learning policies. This method offers a biologically inspired alternative to traditional techniques like domain randomization and system identification, enabling more efficient and robust adaptation to real-world discrepancies. By demonstrating how neural plasticity rules can enhance policy transfer, Ergene’s contributions have significant implications for deploying autonomous robots in unstructured environments. Their work stands out for its innovative integration of neuroscience principles with deep learning, offering a fresh perspective on a persistent robotics challenge. With growing recognition in the field, Ergene continues to advance the reliability and adaptability of intelligent robotic systems.
Research Focus
Key Achievements
Top Papers
- 1