Value iteration networks

25Citations
Citations of this article
1.4kReaders
Mendeley users who have this article in their library.

Abstract

We introduce the value iteration network (VIN): a fully differentiable neural network with a 'planning module' embedded within. VINs can learn to plan, and are suitable for predicting outcomes that involve planning-based reasoning, such as policies for reinforcement learning. Key to our approach is a novel differentiable approximation of the value-iteration algorithm, which can be represented as a convolutional neural network, and trained end-to-end using standard backpropagation. We evaluate VIN based policies on discrete and continuous path-planning domains, and on a natural-language based search task. We show that by learning an explicit planning computation, VIN policies generalize better to new, unseen domains. This paper is a significantly abridged and IJCAI audience targeted version of the original NIPS 2016 paper with the same title, available here: https://arxiv.org/abs/1602.02867.

Cite

CITATION STYLE

APA

Tamar, A., Wu, Y., Thomas, G., Levine, S., & Abbeel, P. (2017). Value iteration networks. In IJCAI International Joint Conference on Artificial Intelligence (Vol. 0, pp. 4949–4953). International Joint Conferences on Artificial Intelligence. https://doi.org/10.24963/ijcai.2017/700

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free