Ricardo Aler

Papers

Total Citations

H-Index

About

Ricardo Aler is a researcher whose work sits at the intersection of evolutionary computation, machine learning, and autonomous robotics. His research explores how evolutionary algorithms can be combined with learning mechanisms to produce intelligent, adaptive behavior in artificial agents. A notable thread throughout his career is the development and investigation of Grammatical Evolution Guided by Reinforcement, an innovative framework that extends standard Grammatical Evolution by integrating reinforcement learning into the evolutionary process, allowing individuals within a population to learn and adapt during their own lifetimes. This line of inquiry led Aler to examine foundational questions about how learning and evolution interact, including rigorous investigations into Lamarckian and Baldwinian models of inheritance — exploring whether and how skills acquired through lifetime learning should be passed on to offspring. His early work on automatic symbolic modelling of co-evolutionarily learned robot skills further demonstrates his interest in making machine-learned behaviors interpretable and transferable. While his citation counts remain modest, reflecting a specialized research niche, his contributions offer meaningful theoretical and practical insights for researchers working on the convergence of evolutionary algorithms, grammatical approaches to program synthesis, and reinforcement learning in embodied and autonomous systems.