Alex Kyriazis
Papers
1
Total Citations
3
H-Index
1
About
Alex Kyriazis is a researcher at the forefront of robotics and reinforcement learning, with a focus on enabling robots to acquire complex, dynamic motion skills. His most cited work, "Model-Based Action Exploration for Learning Dynamic Motion Skills" (2018), tackles a critical bottleneck in deep reinforcement learning: how to efficiently generate high-quality training data for continuous control tasks. By introducing a model-based exploration strategy, Kyriazis’s research directly addresses the challenge of sample efficiency, allowing robots to learn agile behaviors—such as locomotion or manipulation—with fewer interactions. While his citation count is still growing, his contributions are foundational for advancing data-driven robotics, bridging the gap between simulation and real-world deployment. Kyriazis’s work is particularly notable for its practical impact on motion planning and control, offering a principled approach to exploration that has inspired subsequent studies in autonomous systems. As a rising voice in the field, his research continues to shape how machines learn to move with precision and adaptability.
Research Focus
Key Achievements
Top Papers
- 1Model-Based Action Exploration for Learning Dynamic Motion Skills3 citations · 2018