Generalized Value Iteration Networks: Life Beyond Lattices

In this paper, we introduce a generalized value iteration network (GVIN), which is an end-to-end neural network planning module. GVIN emulates the value iteration algorithm by using a novel graph convolution operator, which enables GVIN to learn and plan on irregular spatial graphs. We propose three...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Niu, Sufeng, Chen, Siheng, Guo, Hanyu, Targonski, Colin, Smith, Melissa C, Kovačević, Jelena
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 26.10.2017
Subjects
Convolution
Graphs
Iterative algorithms
Kernels
Lattices
Modules
Neural networks
Planning
Online AccessGet full text

Cover

More Information
Summary:In this paper, we introduce a generalized value iteration network (GVIN), which is an end-to-end neural network planning module. GVIN emulates the value iteration algorithm by using a novel graph convolution operator, which enables GVIN to learn and plan on irregular spatial graphs. We propose three novel differentiable kernels as graph convolution operators and show that the embedding based kernel achieves the best performance. We further propose episodic Q-learning, an improvement upon traditional n-step Q-learning that stabilizes training for networks that contain a planning module. Lastly, we evaluate GVIN on planning problems in 2D mazes, irregular graphs, and real-world street networks, showing that GVIN generalizes well for both arbitrary graphs and unseen graphs of larger scale and outperforms a naive generalization of VIN (discretizing a spatial graph into a 2D image).
ISSN:2331-8422