Skip to yearly menu bar Skip to main content


Value Iteration Networks

Aviv Tamar · Sergey Levine · Pieter Abbeel · YI WU · Garrett Thomas

Area 5+6+7+8 #178

Keywords: [ Deep Learning or Neural Networks ] [ Reinforcement Learning Algorithms ]


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.

Live content is unavailable. Log in and register to view live content