Value Iteration Networks
Aviv Tamar, Yi Wu, Garrett Thomas, Sergey Levine, Pieter Abbeel
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/avivt/VINOfficialIn paperpytorch★ 0
- github.com/zuoxingdong/VIN_PyTorch_Visdompytorch★ 224
- github.com/sufengniu/GVINtf★ 24
- github.com/TheAbhiKumar/tensorflow-value-iteration-networkstf★ 0
- github.com/Dungyichao/Electric-Vehicle-Route-Planning-on-Google-Map-Reinforcement-Learningtf★ 0
- github.com/onlytailei/Value-Iteration-Networks-PyTorchpytorch★ 0
- github.com/LiorAl/GymValueIterationNetworkspytorch★ 0
- github.com/kentsommer/pytorch-value-iteration-networkspytorch★ 0
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.