TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Gaier, Adam
A1  - Asteroth, Alexander
A1  - Mouret, Jean-Baptiste
T1  - Discovering Representations for Black-box Optimization
T2  - GECCO '20: Proceedings of the 2020 Genetic and Evolutionary Computation Conference, July 8–12, 2020, Cancún, Mexico
N2  - The encoding of solutions in black-box optimization is a delicate, handcrafted balance between expressiveness and domain knowledge between exploring a wide variety of solutions, and ensuring that those solutions are useful. Our main insight is that this process can be automated by generating a dataset of high-performing solutions with a quality diversity algorithm (here, MAP-Elites), then learning a representation with a generative model (here, a Varia-tional Autoencoder) from that dataset. Our second insight is that this representation can be used to scale quality diversity optimization to higher dimensions-but only if we carefully mix solutions generated with the learned representation and those generated with traditional variation operators. We demonstrate these capabilities by learning an low-dimensional encoding for the inverse kinemat-ics of a thousand joint planar arm. The results show that learned representations make it possible to solve high-dimensional problems with orders of magnitude fewer evaluations than the standard MAP-Elites, and that, once solved, the produced encoding can be used for rapid optimization of novel, but similar, tasks. The presented techniques not only scale up quality diversity algorithms to high dimensions, but show that black-box optimization encodings can be automatically learned, rather than hand designed.
SN  - 978-1-4503-7128-5
SB  - 978-1-4503-7128-5
U6  - https://doi.org/10.1145/3377930.3390221
DO  - https://doi.org/10.1145/3377930.3390221
AX  - 2003.04389
N1  - This work received funding from the European Research Council (ERC) under the EU Horizon 2020 research and innovation programme (grant agreement number 637972, project "ResiBots") and the German Federal Ministry of Education and Research (BMBF) under the Forschung an Fachhochschulen mit Unternehmen programme (grant agreement number 03FH012PX5, project "Aeromat").
N1  - ©2020 Copyright held by the owner/author(s).
SP  - 103
EP  - 111
S1  - 9
PB  - ACM
CY  - New York, NY, USA
ER  -