Language Guided Skill Discovery

arXiv:2406.06615v1 Announce Type: new
Abstract: Skill discovery methods enable agents to learn diverse emergent behaviors without explicit rewards. To make learned skills useful for unknown downstream tasks, obtaining a semantically diverse repertoire of skills is essential. While some approaches introduce a discriminator to distinguish skills and others aim to increase state coverage, no existing work directly addresses the "semantic diversity" of skills. We hypothesize that leveraging the semantic knowledge of large language models (LLMs) can lead us to improve semantic …

abstract agents aim arxiv coverage cs.ai cs.cl cs.lg cs.ro discovery diverse language learn skill skills state tasks type while work