Edgar A. Aguilar
Papers
1
Total Citations
4
H-Index
1
About
Edgar A. Aguilar is a researcher at the forefront of reinforcement learning and robotics, specializing in the synthesis of complex, multi-objective control policies. His most cited work, "Hierarchical Potential-based Reward Shaping from Task Specifications" (2021), introduces a novel HPRS framework that automatically generates reward signals from high-level task specifications. This breakthrough addresses a critical challenge in robotic control: balancing conflicting requirements without manual reward engineering. By leveraging hierarchical potential functions, Aguilar’s method enables more efficient and interpretable policy learning, advancing the state of the art in autonomous decision-making. With 4 citations, this paper has already influenced peers working on task-driven RL. Aguilar’s contributions are particularly valuable for students and researchers seeking to bridge formal task specifications with practical robotic learning, offering a principled path to safer, more reliable automation. His work exemplifies how structured reward shaping can unlock new capabilities in AI-driven systems.
Research Focus
Key Achievements
Top Papers
- 1Hierarchical Potential-based Reward Shaping from Task Specifications4 citations · 2021