Balancing Both Behavioral Quality and Diversity in Unsupervised Skill Discovery

arXiv:2309.17203v2 Announce Type: replace
Abstract: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. Unsupervised skill discovery seeks to dig out diverse and exploratory skills without extrinsic reward, with the discovered skills efficiently adapting to multiple downstream tasks in various ways. However, recent advanced methods struggle to well balance behavioral exploration and diversity, particularly when the agent dynamics are complex and potential skills …

abstract arxiv copyright cs.ai cs.lg cs.ro discovery diverse diversity exploratory ieee publication quality replace skill skills type unsupervised work