制御可能な多様行動のオフライン学習
Offline Learning of Controllable Diverse Behaviors
オフラインデータから、エピソード全体で一貫した多様な行動を学習し、潜在空間を通じてユーザーが特定の行動を選択・制御できる手法を提案する。
著者: Mathieu Petitbois, Rémy Portelas, Sylvain Lamprier, Ludovic Denoyer
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
Imitation Learning (IL) techniques aim to replicate human behaviors in specific tasks. While IL has gained prominence due to its effectiveness and efficiency, traditional methods often focus on datasets collected from experts to produce a single efficient policy. Recently, extensions have been proposed to handle datasets of diverse behaviors by mainly focusing on learning transition-level diverse policies or on performing entropy maximization at the trajectory level. While these methods may lead to diverse behaviors, they may not be sufficient to reproduce the actual diversity of demonstrations or to allow controlled trajectory generation. To overcome these drawbacks, we propose a different method based on two key features: a) Temporal Consistency that ensures consistent behaviors across entire episodes and not just at the transition level as well as b) Controllability obtained by constructing a latent space of behaviors that allows users to selectively activate specific behaviors based on their requirements. We compare our approach to state-of-the-art methods over a diverse set of tasks and environments. Project page: https://mathieu-petitbois.github.io/projects/swr/
