Summary of Cooperative Multi-agent Graph Bandits: Ucb Algorithm and Regret Analysis, by Phevos Paschalidis et al.
Cooperative Multi-Agent Graph Bandits: UCB Algorithm and Regret Analysis
by Phevos Paschalidis, Runyu Zhang, Na Li
First submitted to arxiv on: 18 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Multiagent Systems (cs.MA); Machine Learning (stat.ML)
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 introduces the multi-agent graph bandit problem, which involves multiple cooperative agents traversing a connected graph to collect rewards. The reward is modeled as a weighted sum of individual agent rewards, capturing the effect of simultaneous sampling at the same node. The authors propose an Upper Confidence Bound (UCB)-based algorithm, Multi-G-UCB, and prove its expected regret bound. Numerical experiments are used to compare this approach with alternative methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In simple terms, this research paper is about how groups of robots or agents can work together to find the best way to collect rewards while exploring a complex network. The problem is framed as a “multi-agent graph bandit” and a new algorithm called Multi-G-UCB is developed to solve it. |
