Summary of Choosing a Classical Planner with Graph Neural Networks, by Jana Vatter et al.
Choosing a Classical Planner with Graph Neural Networks
by Jana Vatter, Ruben Mayer, Hans-Arno Jacobsen, Horst Samulowitz, Michael Katz
First submitted to arxiv on: 25 Jan 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper explores the task of selecting an optimal solver for planning problems using Graph Neural Networks (GNNs). The authors build upon previous work and investigate the impact of various GNN models, graph representations, node features, and prediction tasks. A novel approach is proposed, combining a GNN with Extreme Gradient Boosting (XGBoost) to improve resource efficiency while maintaining accuracy. The paper demonstrates the effectiveness of different GNN-based methods for online planner selection, paving the way for future research in this area. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study helps us choose the best solver for planning problems by using special kinds of artificial intelligence called Graph Neural Networks (GNNs). The researchers looked at how different types of GNN models and ways of representing graphs affect their performance. They also came up with a new method that uses both GNNs and another AI technique called Extreme Gradient Boosting to make better predictions while being more efficient. This work shows us that using GNNs can be really helpful in selecting the best solver for planning problems. |
Keywords
* Artificial intelligence * Extreme gradient boosting * Gnn * Xgboost
