Ferrer-Mestres Jonathan
Papers
1
Total Citations
5
H-Index
1
About
Jonathan Ferrer-Mestres is a researcher at the intersection of artificial intelligence, reinforcement learning, and automated planning, with a focus on enabling intelligent agents to make robust sequential decisions under uncertainty. His most notable contribution is the development of the Planning with Partially Specified Behaviors (PPSB) framework, which elegantly combines reinforcement learning and classical planning to solve complex decision problems. This work, published in 2016, demonstrates how these two traditionally separate fields can complement each other—using planning for high-level reasoning and learning for adapting to partially known environments. Though early in his career, his work has already garnered attention, with his flagship paper accumulating 5 citations and laying groundwork for hybrid AI systems. Ferrer-Mestres’ research addresses a critical challenge: how to build agents that can both learn from experience and leverage symbolic knowledge to act effectively in the world. His contributions are particularly relevant for robotics, autonomous systems, and any domain requiring flexible, intelligent behavior in partially specified settings.
Research Focus
Key Achievements
Top Papers
- 1Planning with Partially Specified Behaviors5 citations · 2016