Trusted AI in multiagent systems: An overview of privacy and security for distributed learning

C Ma, J Li, K Wei, B Liu, M Ding, L Yuan… - Proceedings of the …, 2023 - ieeexplore.ieee.org
Motivated by the advancing computational capacity of distributed end-user equipment (UE),
as well as the increasing concerns about sharing private data, there has been considerable …

Decentralized task offloading in edge computing: A multi-user multi-armed bandit approach

X Wang, J Ye, JCS Lui - IEEE INFOCOM 2022-IEEE …, 2022 - ieeexplore.ieee.org
Mobile edge computing facilitates users to offload computation tasks to edge servers for
meeting their stringent delay requirements. Previous works mainly explore task offloading …

Bandit learning in decentralized matching markets

LT Liu, F Ruan, H Mania, MI Jordan - Journal of Machine Learning …, 2021 - jmlr.org
We study two-sided matching markets in which one side of the market (the players) does not
have a priori knowledge about its preferences for the other side (the arms) and is required to …

Distributed computing in multi-agent systems: a survey of decentralized machine learning approaches

I Ahmed, MA Syed, M Maaruf, M Khalid - Computing, 2025 - Springer
At present, there is a pressing need for data scientists and academic researchers to devise
advanced machine learning and artificial intelligence-driven systems that can effectively …

Heterogeneous multi-player multi-armed bandits: Closing the gap and generalization

C Shi, W **ong, C Shen, J Yang - Advances in neural …, 2021 - proceedings.neurips.cc
Despite the significant interests and many progresses in decentralized multi-player multi-
armed bandits (MP-MAB) problems in recent years, the regret gap to the natural centralized …

Matching in multi-arm bandit with collision

Y Zhang, S Wang, Z Fang - Advances in Neural Information …, 2022 - proceedings.neurips.cc
In this paper, we consider the matching of multi-agent multi-armed bandit problem, ie, while
agents prefer arms with higher expected reward, arms also have preferences on agents. In …

Socially fair reinforcement learning

D Mandal, J Gan - arxiv preprint arxiv:2208.12584, 2022 - arxiv.org
We consider the problem of episodic reinforcement learning where there are multiple
stakeholders with different reward functions. Our goal is to output a policy that is socially fair …

Multitask bandit learning through heterogeneous feedback aggregation

Z Wang, C Zhang, MK Singh, L Riek… - International …, 2021 - proceedings.mlr.press
In many real-world applications, multiple agents seek to learn how to perform highly related
yet slightly different tasks in an online bandit learning protocol. We formulate this problem as …

Decentralized scheduling with qos constraints: Achieving o (1) qos regret of multi-player bandits

Q Liu, Z Fang - Proceedings of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
We consider a decentralized multi-player multi-armed bandit (MP-MAB) problem where
players cannot observe the actions and rewards of other players and no explicit …

Fairness and welfare quantification for regret in multi-armed bandits

S Barman, A Khan, A Maiti, A Sawarni - Proceedings of the AAAI …, 2023 - ojs.aaai.org
We extend the notion of regret with a welfarist perspective. Focussing on the classic multi-
armed bandit (MAB) framework, the current work quantifies the performance of bandit …