Constrained Ensemble Exploration for Unsupervised Skill Discovery

arXiv:2405.16030v1 Announce Type: new
Abstract: Unsupervised Reinforcement Learning (RL) provides a promising paradigm for learning useful behaviors via reward-free per-training. Existing methods for unsupervised RL mainly conduct empowerment-driven skill discovery or entropy-based exploration. However, empowerment often leads to static skills, and pure exploration only maximizes the state coverage rather than learning useful behaviors. In this paper, we propose a novel unsupervised RL framework via an ensemble of skills, where each skill performs partition exploration based on the state prototypes. Thus, …

abstract arxiv coverage cs.lg discovery empowerment ensemble entropy exploration free however leads paradigm per reinforcement reinforcement learning skill skills state training type unsupervised via