Human-Aligned Skill Discovery: Balancing Behaviour Exploration and Alignment
This addresses the issue of unconstrained skill discovery in complex environments for reinforcement learning practitioners, though it appears incremental by building on existing methods with human feedback.
The paper tackles the problem of unsupervised skill discovery in Reinforcement Learning often producing unsafe or impractical skills by proposing Human-aligned Skill Discovery (HaSD), which incorporates human feedback to discover safer and more aligned skills, demonstrating effectiveness in 2D navigation and SafetyGymnasium environments.
Unsupervised skill discovery in Reinforcement Learning aims to mimic humans' ability to autonomously discover diverse behaviors. However, existing methods are often unconstrained, making it difficult to find useful skills, especially in complex environments, where discovered skills are frequently unsafe or impractical. We address this issue by proposing Human-aligned Skill Discovery (HaSD), a framework that incorporates human feedback to discover safer, more aligned skills. HaSD simultaneously optimises skill diversity and alignment with human values. This approach ensures that alignment is maintained throughout the skill discovery process, eliminating the inefficiencies associated with exploring unaligned skills. We demonstrate its effectiveness in both 2D navigation and SafetyGymnasium environments, showing that HaSD discovers diverse, human-aligned skills that are safe and useful for downstream tasks. Finally, we extend HaSD by learning a range of configurable skills with varying degrees of diversity alignment trade-offs that could be useful in practical scenarios.