Learning to Plan in High Dimensions via Neural Exploration-Exploitation Trees
Learning to Plan in High Dimensions via Neural Exploration-Exploitation Trees
复制标题
通过神经探索-利用树学习高维度规划
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Le Song
中科院分区：
文献类型：
--
作者：
Binghong Chen;Bo Dai;Qinjie Lin;Guo Ye;Han Liu;Le Song
本文提出了一种Meta路径规划算法\N {Neural Exploration-Exploitation Trees~（NEXT）}，用于学习高维连续状态空间和动作空间中的先验经验，以解决新的路径规划问题。与更经典的基于采样的方法（如RRT）相比，我们的方法在高维中实现了更好的采样效率，并且可以受益于之前在类似环境中的规划经验。更具体地说，NEXT利用了一种新的神经架构，可以从问题结构中学习有希望的搜索方向。然后将学习到的先验知识集成到UCB型算法中，以在解决新问题时实现探索和利用之间的在线平衡。我们进行了彻底的实验，以表明NEXT完成新的规划问题，更紧凑的搜索树，并显着优于国家的最先进的方法在几个基准。
We propose a meta path planning algorithm named \emph{Neural Exploration-Exploitation Trees~(NEXT)} for learning from prior experience for solving new path planning problems in high dimensional continuous state and action spaces. Compared to more classical sampling-based methods like RRT, our approach achieves much better sample efficiency in high-dimensions and can benefit from prior experience of planning in similar environments. More specifically, NEXT exploits a novel neural architecture which can learn promising search directions from problem structures. The learned prior is then integrated into a UCB-type algorithm to achieve an online balance between \emph{exploration} and \emph{exploitation} when solving a new problem. We conduct thorough experiments to show that NEXT accomplishes new planning problems with more compact search trees and significantly outperforms state-of-the-art methods on several benchmarks.