In this section
@inproceedings{Grillotti:2022:10.1145/3512290.3528837,
author = {Grillotti, L and Cully, A},
doi = {10.1145/3512290.3528837},
pages = {77--85},
publisher = {ACM},
title = {Relevance-guided unsupervised discovery of abilities with quality-diversity algorithms},
url = {http://dx.doi.org/10.1145/3512290.3528837},
year = {2022}
}
TY - CPAPER
AB - Quality-Diversity algorithms provide efficient mechanisms to generate large collections of diverse and high-performing solutions, which have shown to be instrumental for solving downstream tasks. However, most of those algorithms rely on a behavioural descriptor to characterise the diversity that is hand-coded, hence requiring prior knowledge about the considered tasks. In this work, we introduce Relevance-guided Unsupervised Discovery of Abilities; a Quality-Diversity algorithm that autonomously finds a behavioural characterisation tailored to the task at hand. In particular, our method introduces a custom diversity metric that leads to higher densities of solutions near the areas of interest in the learnt behavioural descriptor space. We evaluate our approach on a simulated robotic environment, where the robot has to autonomously discover its abilities based on its full sensory data. We evaluated the algorithms on three tasks: navigation to random targets, moving forward with a high velocity, and performing half-rolls. The experimental results show that our method manages to discover collections of solutions that are not only diverse, but also well-adapted to the considered downstream task.
AU - Grillotti,L
AU - Cully,A
DO - 10.1145/3512290.3528837
EP - 85
PB - ACM
PY - 2022///
SP - 77
TI - Relevance-guided unsupervised discovery of abilities with quality-diversity algorithms
UR - http://dx.doi.org/10.1145/3512290.3528837
UR - http://hdl.handle.net/10044/1/96741
ER -
