ComSD: Balancing Behavioral Quality and Diversity in Unsupervised Skill Discovery

Learning diverse and qualified behaviors for utilization and adaptation without supervision is a key ability of intelligent creatures. Ideal unsupervised skill discovery methods are able to produce diverse and qualified skills in the absence of extrinsic reward, while the discovered skill set can efficiently adapt to downstream tasks in various ways. Maximizing the Mutual Information (MI) between skills and visited states can achieve ideal skill-conditioned behavior distillation in theory. However, it's difficult for recent advanced methods to well balance behavioral quality (exploration) and diversity (exploitation) in practice, which may be attributed to the unreasonable MI estimation by their rigid intrinsic reward design. In this paper, we propose Contrastive multi-objectives Skill Discovery (ComSD) which tries to mitigate the quality-versus-diversity conflict of discovered behaviors through a more reasonable MI estimation and a dynamically weighted intrinsic reward. ComSD proposes to employ contrastive learning for a more reasonable estimation of skill-conditioned entropy in MI decomposition. In addition, a novel weighting mechanism is proposed to dynamically balance different entropy (in MI decomposition) estimations into a novel multi-objective intrinsic reward, to improve both skill diversity and quality. For challenging robot behavior discovery, ComSD can produce a qualified skill set consisting of diverse behaviors at different activity levels, which recent advanced methods cannot. On numerical evaluations, ComSD exhibits state-of-the-art adaptation performance, significantly outperforming recent advanced skill discovery methods across all skill combination tasks and most skill finetuning tasks. Codes will be released at https://github.com/liuxin0824/ComSD.