二層計画のためのニューロシンボリック関係遷移モデルの学習
Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning
記号とニューラルを組み合わせた関係遷移モデルを提案し、外側の記号計画が内側の連続計画を導く二層計画を実現。数十〜数百エピソードで学習でき、未見の物体や最大60行動の長いタスクでも高速に計画できることを4つのロボット領域で示した。
著者: Rohan Chitnis, Tom Silver, Joshua B. Tenenbaum, Tomas Lozano-Perez, Leslie Pack Kaelbling
分類: cs.AI, cs.LG, cs.RO
原文アブストラクト
In robotic domains, learning and planning are complicated by continuous state spaces, continuous action spaces, and long task horizons. In this work, we address these challenges with Neuro-Symbolic Relational Transition Models (NSRTs), a novel class of models that are data-efficient to learn, compatible with powerful robotic planning methods, and generalizable over objects. NSRTs have both symbolic and neural components, enabling a bilevel planning scheme where symbolic AI planning in an outer loop guides continuous planning with neural models in an inner loop. Experiments in four robotic planning domains show that NSRTs can be learned after only tens or hundreds of training episodes, and then used for fast planning in new tasks that require up to 60 actions and involve many more objects than were seen during training. Video: https://tinyurl.com/chitnis-nsrts
