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

TL;DR

This paper presents a novel Quality-Diversity algorithm that autonomously discovers task-relevant behavioral descriptors, enabling robots to find diverse and effective abilities without prior knowledge of task-specific features.

Contribution

It introduces a relevance-guided, unsupervised method for discovering behavioral characterizations tailored to specific tasks, improving diversity and task adaptation.

Findings

Successfully discovers diverse abilities in robotic tasks

Produces solutions well-adapted to downstream tasks

Outperforms baseline methods in behavioral diversity

Abstract

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.