Ricardo Navarro
Papers
1
Total Citations
4
H-Index
1
About
Ricardo Navarro is a researcher at the intersection of robotics, reinforcement learning, and cognitive systems, with a particular focus on how autonomous agents can learn to perceive and categorize objects through active exploration. His key contribution lies in the development of Discernment Behavior Reinforcement Learning, a framework that enables robots to optimize their observation strategies by treating the act of looking as a learned behavior. In his most cited work, "Effective reward function in discernment behavior reinforcement learning based on categorization progress" (2016), Navarro introduced a novel reward function that incentivizes a robot not merely to complete a task, but to actively seek out informative sensory experiences that improve its object categorization accuracy. This work, which has garnered 4 citations, addresses a fundamental challenge in developmental robotics: how a machine can learn to decide where to look and how to move to best understand its environment. By framing categorization progress as an intrinsic reward, Navarro’s research bridges the gap between reinforcement learning and perceptual development, offering a principled approach for building more curious and adaptive robotic systems. His work is particularly valuable for researchers exploring active perception, intrinsic motivation, and lifelong learning in artificial agents.
Research Focus
Key Achievements
Top Papers
- 1