neural networks research group
areas
people
projects
demos
publications
software/data
Accelerating Evolution via Egalitarian Social Learning (2012)
Wesley Tansey
,
Eliana Feasley
, and
Risto Miikkulainen
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:
@inproceedings{tansey:gecco12, title={Accelerating Evolution via Egalitarian Social Learning}, author={Wesley Tansey and Eliana Feasley and Risto Miikkulainen}, booktitle={Proceedings of the 14th Annual Genetic and Evolutionary Computation Conference (GECCO 2012)}, address={Philadelphia, Pennsylvania, USA}, url="http://nn.cs.utexas.edu/?tansey:gecco12", year={2012} }
People
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
Projects
Learning Strategic Behavior in Sequential Decision Tasks
2009 - 2014
Demos
Egalitarian Social Learning (ESL) in Robot Foraging
Wesley Tansey
2012
Software/Data
ESL
This is the C# source code for the experiments with Egalitarian Social Learning (ESL) in a robot foraging domain. The re...
2012
Areas of Interest
Multiagent Systems
Social Agents
Supervised Learning
Evolutionary Computation
Neuroevolution
Reinforcement Learning
Artificial Life