人間の教示から高速学習する汎用エージェント
A Versatile Agent for Fast Learning from Human Instructors
事前学習済みスキルの「ポリシープール」を階層的に管理し、人間の1回のデモンストレーションから複雑なタスクを即座に習得する手法を提案した論文。
著者: Yiwen Chen, Zedong Zhang, Haofeng Liu, Jiayi Tan, Chee-Meng Chew, Marcelo Ang
分類: cs.AI, cs.RO
原文アブストラクト
In recent years, a myriad of superlative works on intelligent robotics policies have been done, thanks to advances in machine learning. However, inefficiency and lack of transfer ability hindered algorithms from pragmatic applications, especially in human-robot collaboration, when few-shot fast learning and high flexibility become a wherewithal. To surmount this obstacle, we refer to a "Policy Pool", containing pre-trained skills that can be easily accessed and reused. An agent is employed to govern the "Policy Pool" by unfolding requisite skills in a flexible sequence, contingent on task specific predilection. This predilection can be automatically interpreted from one or few human expert demonstrations. Under this hierarchical setting, our algorithm is able to pick up a sparse-reward, multi-stage knack with only one demonstration in a Mini-Grid environment, showing the potential for instantly mastering complex robotics skills from human instructors. Additionally, the innate quality of our algorithm also allows for lifelong learning, making it a versatile agent.
