Multi-Emitter MAP-Elites: Improving quality, diversity and convergence speed with heterogeneous sets of emitters

07/10/2020
by   Antoine Cully, et al.
0

Quality-Diversity (QD) optimisation is a new family of learning algorithms that aims at generating collections of diverse and high-performing solutions. Among those algorithms, MAP-Elites is a simple yet powerful approach that has shown promising results in numerous applications. In this paper, we introduce a novel algorithm named Multi-Emitter MAP-Elites (ME-MAP-Elites) that improves the quality, diversity and convergence speed of MAP-Elites. It is based on the recently introduced concept of emitters, which are used to drive the algorithm's exploration according to predefined heuristics. ME-MAP-Elites leverages the diversity of a heterogeneous set of emitters, in which each emitter type is designed to improve differently the optimisation process. Moreover, a bandit algorithm is used to dynamically find the best emitter set depending on the current situation. We evaluate the performance of ME-MAP-Elites on six tasks, ranging from standard optimisation problems (in 100 dimensions) to complex locomotion tasks in robotics. Our comparisons against MAP-Elites and existing approaches using emitters show that ME-MAP-Elites is faster at providing collections of solutions that are significantly more diverse and higher performing. Moreover, in the rare cases where no fruitful synergy can be found between the different emitters, ME-MAP-Elites is equivalent to the best of the compared algorithms.

READ FULL TEXT

page 6

page 7

research
02/24/2023

Improving the Data Efficiency of Multi-Objective Quality-Diversity through Gradient Assistance and Crowding Exploration

Quality-Diversity (QD) algorithms have recently gained traction as optim...
research
06/25/2020

Fast and stable MAP-Elites in noisy domains using deep grids

Quality-Diversity optimisation algorithms enable the evolution of collec...
research
05/03/2021

Ensemble Feature Extraction for Multi-Container Quality-Diversity Algorithms

Quality-Diversity algorithms search for large collections of diverse and...
research
07/23/2019

Comparing reliability of grid-based Quality-Diversity algorithms using artificial landscapes

Quality-Diversity (QD) algorithms are a recent type of optimisation meth...
research
09/08/2021

Quality-Diversity Meta-Evolution: customising behaviour spaces to a meta-objective

Quality-Diversity (QD) algorithms evolve behaviourally diverse and high-...
research
04/24/2023

Benchmark tasks for Quality-Diversity applied to Uncertain domains

While standard approaches to optimisation focus on producing a single hi...
research
07/11/2021

Self-Referential Quality Diversity Through Differential Map-Elites

Differential MAP-Elites is a novel algorithm that combines the illuminat...

Please sign up or login with your details

Forgot password? Click here to reset