Offline Diversity Maximization Under Imitation Constraints

arXiv:2307.11373v3 Announce Type: replace
Abstract: There has been significant recent progress in the area of unsupervised skill discovery, utilizing various information-theoretic objectives as measures of diversity. Despite these advances, challenges remain: current methods require significant online interaction, fail to leverage vast amounts of available task-agnostic data and typically lack a quantitative measure of skill utility. We address these challenges by proposing a principled offline algorithm for unsupervised skill discovery that, in addition to maximizing diversity, ensures that each learned skill …

abstract advances arxiv challenges constraints cs.ai cs.lg cs.ro current data discovery diversity fail information offline progress quantitative replace skill type unsupervised vast