記号計画のための型一般化行動の学習
Learning Type-Generalized Actions for Symbolic Planning
エンティティ階層と少数の観察から型一般化された記号行動を学習し、計画時にオンライン一般化を行うことで、未知のタスクや環境変化にも対応できる手法を提案した。
著者: Daniel Tanneberg, Michael Gienger
分類: cs.AI, cs.RO
原文アブストラクト
Symbolic planning is a powerful technique to solve complex tasks that require long sequences of actions and can equip an intelligent agent with complex behavior. The downside of this approach is the necessity for suitable symbolic representations describing the state of the environment as well as the actions that can change it. Traditionally such representations are carefully hand-designed by experts for distinct problem domains, which limits their transferability to different problems and environment complexities. In this paper, we propose a novel concept to generalize symbolic actions using a given entity hierarchy and observed similar behavior. In a simulated grid-based kitchen environment, we show that type-generalized actions can be learned from few observations and generalize to novel situations. Incorporating an additional on-the-fly generalization mechanism during planning, unseen task combinations, involving longer sequences, novel entities and unexpected environment behavior, can be solved.
