Accelerating Evolution via Egalitarian Social Learning (2012)
Social learning is an extension to evolutionary algorithms that enables agents to learn from observations of others in the population. Historically, social learning algorithms have employed a student-teacher model where the behavior of one or more high-fitness agents is used to train a subset of the remaining agents in the population. This paper presents ESL, an egalitarian model of social learning in which agents are not labeled as teachers or students, instead allowing any individual receiving a sufficiently high reward to teach other agents to mimic its recent behavior. We validate our approach through a series of experiments in a robot foraging domain, including comparisons of egalitarian social learning with baseline neuroevolution and a variant of student-teacher social learning. In a complex foraging task, ESL converges to near-optimal strategies faster than either benchmark approach, outperforming both by more than an order of magnitude. The results indicate that egalitarian social learning is a promising new paradigm for social learning in intelligent agents.
View:
PDF, Other
Citation:
In Proceedings of the 14th Annual Genetic and Evolutionary Computation Conference (GECCO 2012), Philadelphia, Pennsylvania, USA, 2012.
Bibtex:

Eliana Feasley Former Ph.D. Student elie [at] cs utexas edu
Risto Miikkulainen Faculty risto [at] cs utexas edu
Wesley Tansey Former Collaborator tansey [at] cs utexas edu
ESL This is the C# source code for the experiments with Egalitarian Social Learning (ESL) in a robot foraging domain. The re... 2012