Learning to Discover Skills through Guidance

Hyunseung Kim, Byungkun Lee, Hojoon Lee, Dongyoon Hwang, Sejik Park, Kyushik Min, Jaegul Choo

Keywords: Unsupervised skill discovery, Reinforcement Learning

TL;DR: We introduce an unsupervised skill learning algorithm, designed to provide direct guidance to encourage exploration.

Abstract: In the field of unsupervised skill discovery (USD), a major challenge is limited exploration, primarily due to substantial penalties when skills deviate from their initial trajectories. To enhance exploration, recent methodologies employ auxiliary rewards to maximize the epistemic uncertainty or entropy of states. However, we have identified that the effectiveness of these rewards declines as the environmental complexity rises. Therefore, we present a novel USD algorithm, skill **disco**very with gui**dance** (**DISCO-DANCE**), which (1) selects the guide skill that possesses the highest potential to reach unexplored states, (2) guides other skills to follow guide skill, then (3) the guided skills are dispersed to maximize their discriminability in unexplored states. Empirical evaluation demonstrates that DISCO-DANCE outperforms other USD baselines in challenging environments, including two navigation benchmarks and a continuous control benchmark. Qualitative visualizations and code of DISCO-DANCE are available at https://mynsng.github.io/discodance/.

Submission Number: 12428