Answers are grounded in this paper and cite their sources.
Algorithm evaluation demonstrates that value iteration networks learn explicit planning computations, indicating improved generalization to unseen domains.
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
No takes yet. Share an insight, caveat, or question.
Tamar et al. (2017) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: