# Divide, Discover, Deploy: Factorized Skill Learning with Symmetry and Style Priors

## TL;DR

This paper introduces a modular unsupervised skill discovery framework that uses factorization, symmetry, and style priors to learn interpretable, safe, and transferable skills for robotics, demonstrating promising results in simulation and real-world transfer.

## Contribution

It presents a novel factorized USD approach with symmetry and style priors, improving interpretability, safety, and transferability of learned robotic skills.

## Key findings

- Discovered structured, human-interpretable behaviors.
- Enhanced safety and diversity through style and regularization.
- Achieved zero-shot transfer to real hardware with competitive performance.

## Abstract

Unsupervised Skill Discovery (USD) allows agents to autonomously learn diverse behaviors without task-specific rewards. While recent USD methods have shown promise, their application to real-world robotics remains underexplored. In this paper, we propose a modular USD framework to address the challenges in the safety, interpretability, and deployability of the learned skills. Our approach employs user-defined factorization of the state space to learn disentangled skill representations. It assigns different skill discovery algorithms to each factor based on the desired intrinsic reward function. To encourage structured morphology-aware skills, we introduce symmetry-based inductive biases tailored to individual factors. We also incorporate a style factor and regularization penalties to promote safe and robust behaviors. We evaluate our framework in simulation using a quadrupedal robot and demonstrate zero-shot transfer of the learned skills to real hardware. Our results show that factorization and symmetry lead to the discovery of structured human-interpretable behaviors, while the style factor and penalties enhance safety and diversity. Additionally, we show that the learned skills can be used for downstream tasks and perform on par with oracle policies trained with hand-crafted rewards.