In this section
@inproceedings{Rakicevic:2020,
author = {Rakicevic, N and Cully, A and Kormushev, P},
publisher = {arXiv},
title = {Policy manifold search for improving diversity-based neuroevolution},
url = {http://arxiv.org/abs/2012.08676v1},
year = {2020}
}
TY - CPAPER
AB - Diversity-based approaches have recently gained popularity as an alternativeparadigm to performance-based policy search. A popular approach from thisfamily, Quality-Diversity (QD), maintains a collection of high-performingpolicies separated in the diversity-metric space, defined based on policies'rollout behaviours. When policies are parameterised as neural networks, i.e.Neuroevolution, QD tends to not scale well with parameter space dimensionality.Our hypothesis is that there exists a low-dimensional manifold embedded in thepolicy parameter space, containing a high density of diverse and feasiblepolicies. We propose a novel approach to diversity-based policy search viaNeuroevolution, that leverages learned latent representations of the policyparameters which capture the local structure of the data. Our approachiteratively collects policies according to the QD framework, in order to (i)build a collection of diverse policies, (ii) use it to learn a latentrepresentation of the policy parameters, (iii) perform policy search in thelearned latent space. We use the Jacobian of the inverse transformation(i.e.reconstruction function) to guide the search in the latent space. Thisensures that the generated samples remain in the high-density regions of theoriginal space, after reconstruction. We evaluate our contributions on threecontinuous control tasks in simulated environments, and compare todiversity-based baselines. The findings suggest that our approach yields a moreefficient and robust policy search process.
AU - Rakicevic,N
AU - Cully,A
AU - Kormushev,P
PB - arXiv
PY - 2020///
TI - Policy manifold search for improving diversity-based neuroevolution
UR - http://arxiv.org/abs/2012.08676v1
UR - http://hdl.handle.net/10044/1/88286
ER -