Summary of A Systematization Of the Wagner Framework: Graph Theory Conjectures and Reinforcement Learning, by Flora Angileri et al.
A Systematization of the Wagner Framework: Graph Theory Conjectures and Reinforcement Learning
by Flora Angileri, Giulia Lombardi, Andrea Fois, Renato Faraone, Carlo Metta, Michele Salvi, Luigi Amedeo Bianchi, Marco Fantozzi, Silvia Giulia Galfrè, Daniele Pavesi, Maurizio Parton, Francesco Morandin
First submitted to arxiv on: 18 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 The proposed approach to disprove conjectures in graph theory uses Reinforcement Learning (RL) to maximize a score that represents the quantity of interest. This involves playing a single-player graph-building game where edges are added or not, with the goal of maximizing the final score. The paper discusses various choices and presents four distinct single-player graph-building games, each using both step-by-step rewards and a single final score. Additionally, it proposes a principled approach to select neural network architectures for conjectures and introduces a new dataset of graphs labeled with their Laplacian spectra. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper uses artificial intelligence to help prove or disprove statements about graphs. It creates a game where edges are added to a graph, trying to get the best score possible. The goal is to use this game to figure out if certain statements are true or false. The paper presents different ways to play this game and how to choose the right computer model for each statement. |
Keywords
» Artificial intelligence » Neural network » Reinforcement learning
