Eliana Feasley

Papers

Total Citations

H-Index

About

Eliana Feasley’s research lies at the intersection of evolutionary computation and multiagent systems, with a focus on how social learning can accelerate adaptation in artificial populations. Her most cited work, “Accelerating evolution via egalitarian social learning” (2012, 18 citations), challenges traditional student-teacher models by proposing a framework where all agents in a population can learn from one another without hierarchical fitness biases. This egalitarian approach to social learning significantly improves the speed and robustness of evolutionary algorithms, offering a more democratic and efficient path to optimization. In her complementary study “Multiagent Learning through Neuroevolution” (2012, 13 citations), Feasley extends these ideas to complex multiagent domains, demonstrating how neuroevolution can be combined with social learning to solve cooperative and competitive tasks. Her contributions are notable for rethinking how knowledge flows within evolving populations, moving away from elitist paradigms toward more collaborative mechanisms. While her citation counts reflect the niche but foundational nature of her work, Feasley’s insights have influenced subsequent research in evolutionary robotics and collective intelligence, marking her as a thoughtful innovator in the field.