In: Proceedings of the Genetic and Evolutionary Computation Conference Companion. Genetic and Evolutionary Computation Conference (GECCO-2019) July 13-17 Prag Czech Republic 2019.
Abstract
Contextual policy search (CPS) is a class of multi-task reinforcement learning algorithms that is particularly useful for robotic applications. A recent state-of-the-art method is Contextual Covariance Matrix Adaptation Evolution Strategies (C-CMA-ES). It is based on the standard black-box optimization algorithm CMA-ES. There are two useful extensions ofCMA-ES thatwe will transfer to C-CMA-ES and evaluate empirically: ACM-ES, which uses a comparison-based surrogate model, and aCMA-ES, which uses an active update of the covariance matrix. We will show that improvements with these methods can be impressive in terms of sample-efficiency, although this is not relevant any more for the robotic domain.
@inproceedings{pub10503,
author = {
Fabisch, Alexander
},
title = {Empirical Evaluation of Contextual Policy Search with a Comparison-based Surrogate Model and Active Covariance Matrix Adaptation},
booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference Companion. Genetic and Evolutionary Computation Conference (GECCO-2019), July 13-17, Prag, Czech Republic},
year = {2019}
}
German Research Center for Artificial Intelligence Deutsches Forschungszentrum für Künstliche Intelligenz
