Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts

arXiv:2403.06966v1 Announce Type: new
Abstract: Reinforcement learning (RL) is a powerful approach for acquiring a good-performing policy. However, learning diverse skills is challenging in RL due to the commonly used Gaussian policy parameterization. We propose \textbf{Di}verse \textbf{Skil}l \textbf{L}earning (Di-SkilL), an RL method for learning diverse skills using Mixture of Experts, where each expert formalizes a skill as a contextual motion primitive. Di-SkilL optimizes each expert and its associate context distribution to a maximum entropy objective that incentivizes learning diverse skills …

abstract arxiv cs.lg cs.ro curriculum diverse experts good however mixture of experts policy reinforcement reinforcement learning skills type