Unsupervised Behaviour Discovery with Quality-Diversity Optimisation

06/10/2021
by   Luca Grillotti, et al.
0

Quality-Diversity algorithms refer to a class of evolutionary algorithms designed to find a collection of diverse and high-performing solutions to a given problem. In robotics, such algorithms can be used for generating a collection of controllers covering most of the possible behaviours of a robot. To do so, these algorithms associate a behavioural descriptor to each of these behaviours. Each behavioural descriptor is used for estimating the novelty of one behaviour compared to the others. In most existing algorithms, the behavioural descriptor needs to be hand-coded, thus requiring prior knowledge about the task to solve. In this paper, we introduce: Autonomous Robots Realising their Abilities, an algorithm that uses a dimensionality reduction technique to automatically learn behavioural descriptors based on raw sensory data. The performance of this algorithm is assessed on three robotic tasks in simulation. The experimental results show that it performs similarly to traditional hand-coded approaches without the requirement to provide any hand-coded behavioural descriptor. In the collection of diverse and high-performing solutions, it also manages to find behaviours that are novel with respect to more features than its hand-coded baselines. Finally, we introduce a variant of the algorithm which is robust to the dimensionality of the behavioural descriptor space.

READ FULL TEXT

page 1

page 9

research
04/21/2022

Relevance-guided Unsupervised Discovery of Abilities with Quality-Diversity Algorithms

Quality-Diversity algorithms provide efficient mechanisms to generate la...
research
05/28/2019

Autonomous skill discovery with Quality-Diversity and Unsupervised Descriptors

Quality-Diversity optimization is a new family of optimization algorithm...
research
11/22/2022

Discovering Unsupervised Behaviours from Full-State Trajectories

Improving open-ended learning capabilities is a promising approach to en...
research
03/04/2020

QED: using Quality-Environment-Diversity to evolve resilient robot swarms

In swarm robotics, any of the robots in a swarm may be affected by diffe...
research
05/02/2023

Evolution of linkages for prototyping of linkage based robots

Prototyping robotic systems is a time consuming process. Computer aided ...
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
04/07/2023

Don't Bet on Luck Alone: Enhancing Behavioral Reproducibility of Quality-Diversity Solutions in Uncertain Domains

Quality-Diversity (QD) algorithms are designed to generate collections o...

Please sign up or login with your details

Forgot password? Click here to reset