paper-with-me

홈 › Papers

Multi-Armed Bandits with Interference

2024-02-02 · Su Jia, Peter Frazier, Nathan Kallus

Experimentation with interference poses a significant challenge in contemporary online platforms. Prior research on experimentation with interference has concentrated on the final output of a policy. The cumulative performance, while equally crucial, is less well understood. To address this gap, we introduce the problem of {\em Multi-armed Bandits with Interference} (MABI), where the learner assigns an arm to each of $N$ experimental units over a time horizon of $T$ rounds. The reward of each unit in each round depends on the treatments of {\em all} units, where the influence of a unit decays in the spatial distance between units. Furthermore, we employ a general setup wherein the reward functions are chosen by an adversary and may vary arbitrarily across rounds and units. We first show that switchback policies achieve an optimal {\em expected} regret $\tilde O(\sqrt T)$ against the best fixed-arm policy. Nonetheless, the regret (as a random variable) for any switchback policy suffers a high variance, as it does not account for $N$. We propose a cluster randomization policy whose regret (i) is optimal in {\em expectation} and (ii) admits a high probability bound that vanishes in $N$.

📄 PDF Abstract BibTeX arXiv:2402.01845

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Armed Bandits

Similar Papers 제목 키워드 기반

Graph-Dependent Regret Bounds in Multi-Armed Bandits with Interference

2025-03-10 · Fateme Jamshidi, Mohammad ShahverdiKondori, Negar Kiyavash

Multi-armed bandits (MABs) are frequently used for online sequential decision-making in applications ranging from recommending personalized content to assigning treatments to patients. A recurring challenge in the applic…

Multi-Armed BanditsSequential Decision Making

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 LearningMulti-Armed Banditsreinforcement-learningReinforcement Learning (RL)

Design-Based Bandits Under Network Interference: Trade-Off Between Regret and Statistical Inference

2025-10-09 · Zichen Wang, Haoyang Hong, Chuanhao Li, Haoxuan Li 외 arxiv

In multi-armed bandits with network interference (MABNI), the action taken by one node can influence the rewards of others, creating complex interdependence. While existing research on MABNI largely concentrates on minim…

Multi-Armed Bandits

Batched Multi-armed Bandits Problem

2019-04-03 · NeurIPS 2019 12 · Zijun Gao, Yanjun Han, Zhimei Ren, Zhengqing Zhou

In this paper, we study the multi-armed bandit problem in the batched setting where the employed policy must split data into a small number of batches. While the minimax regret for the two-armed stochastic bandits has be…

Multi-Armed Bandits

Indexability of Finite State Restless Multi-Armed Bandit and Rollout Policy

2023-04-30 · Vishesh Mittal, Rahul Meshram, Deepak Dev, Surya Prakash

We consider finite state restless multi-armed bandit problem. The decision maker can act on M bandits out of N bandits in each time step. The play of arm (active arm) yields state dependent rewards based on action and wh…