Skip to content
PyTorch implementation of the Value Iteration Networks (VIN) (NIPS '16 best paper)
Python
Branch: master
Clone or download
Latest commit d8014ef Mar 13, 2017
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
data
img delete annotation Mar 13, 2017
.gitignore delete pyc Mar 13, 2017
README.md delete annotation Mar 13, 2017
data.py first commint Mar 13, 2017
model.py
train_main.py delete annotation Mar 13, 2017
utils.py add readme Mar 13, 2017

README.md

Value Iteration Networks in PyTorch

Tamar, A., Wu, Y., Thomas, G., Levine, S., and Abbeel, P. Value Iteration Networks. Neural Information Processing Systems (NIPS) 2016

This repository contains an implementation of Value Iteration Networks (VIN) in PyTorch based on the original Theano implementation by the authors and the TensoFlow implementation by Abhishek Kumar.

VIN won the Best Paper Award at NIPS 2016.

Value Iteration Network and Module

Dependencies

  • Python 2.7
  • PyTorch
  • SciPy >= 0.18.1 (to load the data)

Datasets

Training

python train_main.py

Several arguments can be set in train_main.py like learning rate. Please check train_main.py for details.

python train_main.py --lr 0.001

References

You can’t perform that action at this time.