AAAI 2023technical4 citations
Communication-Efficient Collaborative Best Arm Identification
Abstract
We investigate top-m arm identification, a basic problem in bandit theory, in a multi-agent learning model in which agents collaborate to learn an objective function. We are interested in designing collaborative learning algorithms that achieve maximum speedup (compared to single-agent learning algorithms) using minimum communication cost, as communication is frequently the bottleneck in multi-agent learning. We give both algorithmic and impossibility results, and conduct a set of experiments to demonstrate the effectiveness of our algorithms.
BibTeX
@article{Karpov_Zhang_2023, title={Communication-Efficient Collaborative Best Arm Identification}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/25990}, DOI={10.1609/aaai.v37i7.25990}, abstractNote={We investigate top-m arm identification, a basic problem in bandit theory, in a multi-agent learning model in which agents collaborate to learn an objective function. We are interested in designing collaborative learning algorithms that achieve maximum speedup (compared to single-agent learning algorithms) using minimum communication cost, as communication is frequently the bottleneck in multi-agent learning. We give both algorithmic and impossibility results, and conduct a set of experiments to demonstrate the effectiveness of our algorithms.}, number={7}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Karpov, Nikolai and Zhang, Qin}, year={2023}, month={Jun.}, pages={8203-8210} }