Emre Aksan
Papers
1
Total Citations
24
H-Index
1
About
Emre Aksan is a researcher advancing the frontiers of reinforcement learning and robotics, with a focus on hierarchical control and long-horizon decision-making. His key contributions lie in developing scalable architectures that decompose complex tasks into manageable sub-problems, enabling autonomous systems to plan and execute actions more efficiently. In his highly cited work, "Learning Functionally Decomposed Hierarchies for Continuous Control Tasks With Path Planning" (2021, 24 citations), Aksan introduced HiDe, a novel hierarchical reinforcement learning framework that separates planning from low-level control by explicitly partitioning state-action spaces. This functional decomposition allows agents to generalize to unseen test scenarios and solve long-horizon tasks that traditional methods struggle with. By bridging the gap between high-level path planning and continuous motor control, his research has practical implications for robotics, autonomous navigation, and simulation-based training. Aksan’s work demonstrates a clear impact on the reinforcement learning community, offering a principled approach to building more modular and transferable AI systems. His contributions continue to inspire researchers seeking to design agents that can reason, plan, and act in complex, dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1