Merge pull request #4 from tkipf/patch-1

Add python/pytorch version requirements to Readme

README.md

@@ -10,6 +10,10 @@ https://arxiv.org/abs/1802.04687  (*: equal contribution)˚
 
 **Abstract:** Interacting systems are prevalent in nature, from dynamical systems in physics to complex societal dynamics. The interplay of components can give rise to complex behavior, which can often be explained using a simple model of the system's constituent parts. In this work, we introduce the neural relational inference (NRI) model: an unsupervised model that learns to infer interactions while simultaneously learning the dynamics purely from observational data. Our model takes the form of a variational auto-encoder, in which the latent code represents the underlying interaction graph and the reconstruction is based on graph neural networks. In experiments on simulated physical systems, we show that our NRI model can accurately recover ground-truth interactions in an unsupervised manner. We further demonstrate that we can find an interpretable structure and predict complex dynamics in real motion capture and sports tracking data.
 
+### Requirements
+* Pytorch 0.2 (0.3 breaks simulation decoder)
+* Python 2.7 or 3.6
+
 ### Data generation
 
 To replicate the experiments on simulated physical data, first generate training, validation and test data by running:
@@ -54,4 +58,4 @@ If you make use of this code in your own work, please cite our paper:
   journal={arXiv preprint arXiv:1802.04687},
   year={2018}
 }
-```
+```