paper-with-me

홈 › Papers

Cost-Efficient Online Decision Making: A Combinatorial Multi-Armed Bandit Approach

2023-08-21 · Arman Rahbar, Niklas Åkerblom, Morteza Haghir Chehreghani

Online decision making plays a crucial role in numerous real-world applications. In many scenarios, the decision is made based on performing a sequence of tests on the incoming data points. However, performing all tests can be expensive and is not always possible. In this paper, we provide a novel formulation of the online decision making problem based on combinatorial multi-armed bandits and take the (possibly stochastic) cost of performing tests into account. Based on this formulation, we provide a new framework for cost-efficient online decision making which can utilize posterior sampling or BayesUCB for exploration. We provide a theoretical analysis of Thompson Sampling for cost-efficient online decision making, and present various experimental results that demonstrate the applicability of our framework to real-world problems.

📄 PDF Abstract BibTeX arXiv:2308.10699

Code (1)

rahbararman/cost-efficient-odm 공식 구현

Tasks

Decision MakingMulti-Armed BanditsThompson Sampling

Similar Papers 제목 키워드 기반

Online Decision-Making in General Combinatorial Spaces

2014-12-01 · NeurIPS 2014 12 · Arun Rajkumar, Shivani Agarwal

We study online combinatorial decision problems, where one must make sequential decisions in some combinatorial space without knowing in advance the cost of decisions on each trial; the goal is to minimize the total regr…

Decision Making

Offline Local Search for Online Stochastic Bandits

2026-04-10 · Gerdus Benadè, Rathish Das, Thomas Lavastida arxiv

Combinatorial multi-armed bandits provide a fundamental online decision-making environment where a decision-maker interacts with an environment across $T$ time steps, each time selecting an action and learning the cost o…

Multi-Armed Bandits

Smoothed Online Combinatorial Optimization Using Imperfect Predictions

2022-04-23 · Kai Wang, Zhao Song, Georgios Theocharous, Sridhar Mahadevan

Smoothed online combinatorial optimization considers a learner who repeatedly chooses a combinatorial decision to minimize an unknown changing cost function with a penalty on switching decisions in consecutive rounds. We…

Combinatorial Optimization

Offline Learning for Combinatorial Multi-armed Bandits

2025-01-31 · Xutong Liu, Xiangxiang Dai, Jinhang Zuo, Siwei Wang 외

The combinatorial multi-armed bandit (CMAB) is a fundamental sequential decision-making framework, extensively studied over the past decade. However, existing work primarily focuses on the online setting, overlooking the…

Decision MakingLanguage ModelingLanguage ModellingLarge Language Model+3

Decision-Making under Combinatorial Risk

2026-06-08 · Yifan Hong, Hongmiao Fan, Chen Wang arxiv

Decision-making under risk is typically studied through single-shot lottery choices. Yet many real decisions involve combinatorial risk, where risk arises from multiple risky components, so the lottery over outcomes is i…