Cooperative Multi-Agent Graph Bandits: UCB Algorithm and Regret Analysis.
Phevos PaschalidisRunyu ZhangNa LiPublished in: CoRR (2024)
Keyphrases
- worst case
- learning algorithm
- graph based algorithm
- minimum spanning tree
- simulated annealing
- multi armed bandit
- k means
- cost function
- dynamic programming
- segmentation algorithm
- strongly connected components
- graph structure
- matching algorithm
- expectation maximization
- search space
- objective function
- bipartite graph
- weighted graph
- spanning tree
- similarity measure
- dominating set
- clustering algorithm