Empirical Evaluation of Contextual Policy Search with a Comparison-based Surrogate Model and Active Covariance Matrix Adaptation
Alexander Fabisch
In Proceedings of the Genetic and Evolutionary Computation Conference Companion, (GECCO-2019), 13.7.-17.7.2019, Prag, o.A., 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.


© DFKI GmbH
last updated 28.02.2023