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

by   Manon Flageat, et al.

Quality-Diversity optimisation algorithms enable the evolution of collections of both high-performing and diverse solutions. These collections offer the possibility to quickly adapt and switch from one solution to another in case it is not working as expected. It therefore finds many applications in real-world domain problems such as robotic control. However, QD algorithms, like most optimisation algorithms, are very sensitive to uncertainty on the fitness function, but also on the behavioural descriptors. Yet, such uncertainties are frequent in real-world applications. Few works have explored this issue in the specific case of QD algorithms, and inspired by the literature in Evolutionary Computation, mainly focus on using sampling to approximate the "true" value of the performances of a solution. However, sampling approaches require a high number of evaluations, which in many applications such as robotics, can quickly become impractical. In this work, we propose Deep-Grid MAP-Elites, a variant of the MAP-Elites algorithm that uses an archive of similar previously encountered solutions to approximate the performance of a solution. We compare our approach to previously explored ones on three noisy tasks: a standard optimisation task, the control of a redundant arm and a simulated Hexapod robot. The experimental results show that this simple approach is significantly more resilient to noise on the behavioural descriptors, while achieving competitive performances in terms of fitness optimisation, and being more sample-efficient than other existing approaches.


page 7

page 8


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

Quality-Diversity (QD) optimisation is a new family of learning algorith...

Evaluating Noisy Optimisation Algorithms: First Hitting Time is Problematic

A key part of any evolutionary algorithm is fitness evaluation. When fit...

Uncertain Quality-Diversity: Evaluation methodology and new methods for Quality-Diversity in Uncertain Domains

Quality-Diversity optimisation (QD) has proven to yield promising result...

On the Robustness of Median Sampling in Noisy Evolutionary Optimization

In real-world optimization tasks, the objective (i.e., fitness) function...

Ensemble Feature Extraction for Multi-Container Quality-Diversity Algorithms

Quality-Diversity algorithms search for large collections of diverse and...

Improving Intelligence of Evolutionary Algorithms Using Experience Share and Replay

We propose PESA, a novel approach combining Particle Swarm Optimisation ...

Discovering Unsupervised Behaviours from Full-State Trajectories

Improving open-ended learning capabilities is a promising approach to en...

Please sign up or login with your details

Forgot password? Click here to reset