Sep 11, 2020 · Title:Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks ; Subjects: Machine Learning (cs.LG); ...
Our work uses graph neural networks (GNNs) (Scarselli et al. 2008; Kipf and Welling 2016; Battaglia et al. 2018), an in- creasingly popular choice for ...
This work proposes a graph neural network architecture for predicting object importance in a single inference pass, thus incurring little overhead while ...
This repository houses code for the AAAI 2021 paper: Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks.
Sep 11, 2020 · In this work, we learn to predict a small subset of objects that is sufficient for planning, leading to significantly faster planning than both ...
@InProceedings{LIS287, title = {Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks}, author = {Tom Silver and ...
@inproceedings{silver2020planning, title={Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks}, author={Tom ...
People also ask
Why are graph neural networks effective for EDA problems?
How important are graph neural networks?
Why graph neural networks for recommender systems?
How is graph theory used in neural networks?
Planning with learned object importance in large problem instances using graph neural networks. arXiv preprint arXiv:2009.05613. Ståhlberg, S.; Bonet, B ...
We conclude that learning to predict a sufficient set of objects for a planning problem is a simple, powerful, and general mechanism for planning in large ...