Sergio Miranda
Papers
1
Total Citations
6
H-Index
1
About
Sergio Miranda is a researcher whose work bridges reinforcement learning and control theory, with a particular emphasis on developing data-efficient algorithms for complex decision-making problems. His most cited paper, "Fitted Q-iteration by Functional Networks for control problems" (2016), has garnered 6 citations and introduces a novel approach that combines fitted Q-iteration with functional networks to approximate value functions in continuous state and action spaces. This contribution addresses a critical challenge in reinforcement learning: the need for sample-efficient methods that can handle high-dimensional control tasks without requiring explicit model knowledge. Miranda's work is notable for its practical orientation, offering a framework that reduces computational complexity while maintaining robust performance in control applications. His research sits at the intersection of machine learning and optimal control, aiming to make reinforcement learning more accessible for real-world systems such as robotics and autonomous navigation. Though his citation count is modest, Miranda's methodological innovations provide a foundation for further exploration in scalable, data-driven control, making his contributions valuable for students and researchers seeking efficient solutions in reinforcement learning and intelligent control.
Research Focus
Key Achievements
Top Papers
- 1Fitted Q-iteration by Functional Networks for control problems6 citations · 2016