Bandits with Concave Aggregated Reward
Yingqi Yu, Sijia Zhang, Shaoang Li, Lan Zhang, Wei Xie, Xiang-Yang Li
Abstract
Multi-armed bandit is a simple but powerful algorithmic framework, and many effective algorithms have been proposed for various online models. In numerous applications, the decision-maker faces diminishing marginal utility. With non-linear aggregations, those algorithms often have poor regret bounds. Motivated by this, we study a bandit problem with diminishing marginal utility, which we termed the bandits with concave aggregated reward(BCAR). To tackle this problem, we propose two algorithms SW-BCAR and SWUCB-BCAR. Through theoretical analysis, we establish the effectiveness of these algorithms in addressing the BCAR issue. Extensive simulations demonstrate that our algorithms achieve better results than the most advanced bandit algorithms.
BibTeX
@inproceedings{ijcai2024p597,
title = {Bandits with Concave Aggregated Reward},
author = {Yu, Yingqi and Zhang, Sijia and Li, Shaoang and Zhang, Lan and Xie, Wei and Li, Xiang-Yang},
booktitle = {Proceedings of the Thirty-Third International Joint Conference on
Artificial Intelligence, {IJCAI-24}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Kate Larson},
pages = {5398--5406},
year = {2024},
month = {8},
note = {Main Track},
doi = {10.24963/ijcai.2024/597},
url = {https://doi.org/10.24963/ijcai.2024/597},
}