Collaborative Multi-agent Stochastic Linear Bandits

2022-05-12 · Ahmadreza Moradipari, Mohammad Ghavamzadeh, Mahnoosh Alizadeh

We study a collaborative multi-agent stochastic linear bandit setting, where $N$ agents that form a network communicate locally to minimize their overall regret. In this setting, each agent has its own linear bandit problem (its own reward parameter) and the goal is to select the best global action w.r.t. the average of their reward parameters. At each round, each agent proposes an action, and one action is randomly selected and played as the network action. All the agents observe the corresponding rewards of the played actions and use an accelerated consensus procedure to compute an estimate of the average of the rewards obtained by all the agents. We propose a distributed upper confidence bound (UCB) algorithm and prove a high probability bound on its $T$-round regret in which we include a linear growth of regret associated with each communication round. Our regret bound is of order $\mathcal{O}\Big(\sqrt{\frac{T}{N \log(1/|\lambda_2|)}}\cdot (\log T)^2\Big)$, where $\lambda_2$ is the second largest (in absolute value) eigenvalue of the communication matrix.

📄 PDF Abstract BibTeX arXiv:2205.06331

Code (0)

등록된 구현이 없습니다.

Multi-Agent Best Arm Identification in Stochastic Linear Bandits

2024-11-20 · Sanjana Agrawal, Saúl A. Blanco

We study the problem of collaborative best-arm identification in stochastic linear bandits under a fixed-budget scenario. In our learning model, we consider multiple agents connected through a star network or a generic n…

Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits

2023-05-30 · Ronshee Chawla, Daniel Vial, Sanjay Shakkottai, R. Srikant

The study of collaborative multi-agent bandits has attracted significant attention recently. In light of this, we initiate the study of a new collaborative setting, consisting of $N$ agents such that each agent is learni…

Multi-Armed Bandits

Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds

2022-06-06 · Aritra Mitra, Arman Adibi, George J. Pappas, Hamed Hassani

We consider a linear stochastic bandit problem involving $M$ agents that can collaborate via a central server to minimize regret. A fraction $\alpha$ of these agents are adversarial and can act arbitrarily, leading to th…

Federated Learning for Heterogeneous Bandits with Unobserved Contexts

2023-03-29 · Jiabin Lin, Shana Moothedath

We study the problem of federated stochastic multi-arm contextual bandits with unknown contexts, in which M agents are faced with different bandits and collaborate to learn. The communication model consists of a central …

Federated Learning Multi-Armed Bandits

Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits

2023-01-26 · Nikolai Karpov, Qin Zhang

In this paper, we study the collaborative learning model, which concerns the tradeoff between parallelism and communication overhead in multi-agent multi-armed bandits. For regret minimization in multi-armed bandits, we …

Multi-agent Reinforcement Learning Multi-Armed Bandits reinforcement-learning Reinforcement Learning (RL)