BriefGPT.xyz
Jun, 2024
高速价值迭代网络
Highway Value Iteration Networks
HTML
PDF
Yuhui Wang, Weida Li, Francesco Faccio, Qingyuan Wu, Jürgen Schmidhuber
TL;DR
使用可微分规划模块和嵌入式高速值迭代的方法，有效地解决了长期规划问题并在数百个规划步骤中超越了传统的值迭代网络和一些很深的神经网络。
Abstract
value iteration networks
(VINs) enable end-to-end learning for
planning tasks
by employing a differentiable "planning module" that approximates the value iteration algorithm. However,
→