In this section
@inproceedings{Cully:2021:10.1145/3449639.3459326,
author = {Cully, A},
doi = {10.1145/3449639.3459326},
pages = {84--92},
publisher = {ACM},
title = {Multi-Emitter MAP-Elites: Improving quality, diversity and convergence speed with heterogeneous sets of emitters},
url = {http://dx.doi.org/10.1145/3449639.3459326},
year = {2021}
}
TY - CPAPER
AB - Quality-Diversity (QD) optimisation is a new family of learning algorithmsthat aims at generating collections of diverse and high-performing solutions.Among those algorithms, MAP-Elites is a simple yet powerful approach that hasshown promising results in numerous applications. In this paper, we introduce anovel algorithm named Multi-Emitter MAP-Elites (ME-MAP-Elites) that improvesthe quality, diversity and convergence speed of MAP-Elites. It is based on therecently introduced concept of emitters, which are used to drive thealgorithm's exploration according to predefined heuristics. ME-MAP-Elitesleverages the diversity of a heterogeneous set of emitters, in which eachemitter type is designed to improve differently the optimisation process.Moreover, a bandit algorithm is used to dynamically find the best emitter setdepending on the current situation. We evaluate the performance ofME-MAP-Elites on six tasks, ranging from standard optimisation problems (in 100dimensions) to complex locomotion tasks in robotics. Our comparisons againstMAP-Elites and existing approaches using emitters show that ME-MAP-Elites isfaster at providing collections of solutions that are significantly morediverse and higher performing. Moreover, in the rare cases where no fruitfulsynergy can be found between the different emitters, ME-MAP-Elites isequivalent to the best of the compared algorithms.
AU - Cully,A
DO - 10.1145/3449639.3459326
EP - 92
PB - ACM
PY - 2021///
SP - 84
TI - Multi-Emitter MAP-Elites: Improving quality, diversity and convergence speed with heterogeneous sets of emitters
UR - http://dx.doi.org/10.1145/3449639.3459326
UR - http://arxiv.org/abs/2007.05352v1
UR - http://hdl.handle.net/10044/1/95259
ER -
Artificial Intelligence Network
South Kensington Campus
Imperial College London
SW7 2AZ
To reach the elected speaker of the network, Dr Rossella Arcucci, please contact:
To reach the network manager, Diana O'Malley - including to join the network - please contact: