# Autonomous skill discovery with Quality-Diversity and Unsupervised Descriptors

## TL;DR

This paper presents a method combining Quality-Diversity algorithms with unsupervised dimensionality reduction to enable robots to autonomously discover diverse behaviors without prior knowledge, enhancing versatility and resilience.

## Contribution

It introduces an automatic way to define behavioral descriptors, removing the need for manual specification in Quality-Diversity optimization for robotics.

## Key findings

- Robots autonomously discover a wide range of behaviors.
- Discovered behaviors are similar to handcrafted solutions.
- Behaviors are more diverse than with existing unsupervised methods.

## Abstract

Quality-Diversity optimization is a new family of optimization algorithms that, instead of searching for a single optimal solution to solving a task, searches for a large collection of solutions that all solve the task in a different way. This approach is particularly promising for learning behavioral repertoires in robotics, as such a diversity of behaviors enables robots to be more versatile and resilient. However, these algorithms require the user to manually define behavioral descriptors, which is used to determine whether two solutions are different or similar. The choice of a behavioral descriptor is crucial, as it completely changes the solution types that the algorithm derives. In this paper, we introduce a new method to automatically define this descriptor by combining Quality-Diversity algorithms with unsupervised dimensionality reduction algorithms. This approach enables robots to autonomously discover the range of their capabilities while interacting with their environment. The results from two experimental scenarios demonstrate that robot can autonomously discover a large range of possible behaviors, without any prior knowledge about their morphology and environment. Furthermore, these behaviors are deemed to be similar to handcrafted solutions that uses domain knowledge and significantly more diverse than when using existing unsupervised methods.