Results 21 to 30 of about 110 (105)

The non-Bayesian restless multi-armed bandit: A case of near-logarithmic regret [PDF]

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2011
In the classic Bayesian restless multi-armed bandit (RMAB) problem, there are $N$ arms, with rewards on all arms evolving at each time as Markov chains with known parameters. A player seeks to activate $K \geq 1$ arms at each time in order to maximize the expected total reward obtained over multiple plays. RMAB is a challenging problem that is known to
Wenhan Dai, Yi Gai, Bhaskar Krishnamachari, Qing Zhao 0001   +3 more
openaire   +2 more sources

Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization

, 2023
Restless multi-arm bandits (RMABs), a class of resource allocation problems with broad application in areas such as healthcare, online advertising, and anti-poaching, have recently been studied from a multi-agent reinforcement learning perspective. Prior RMAB research suffers from several limitations, e.g., it fails to adequately address continuous ...
Yunfan Zhao, Nikhil Behari, Edward Hughes 0001, Edwin Zhang, Dheeraj Nagaraj, Karl Tuyls, Aparna Taneja, Milind Tambe   +7 more
openaire   +3 more sources

On the Whittle Index for Restless Multiarmed Hidden Markov Bandits [PDF]

IEEE Transactions on Automatic Control, 2018
We consider a restless multi-armed bandit in which each arm can be in one of two states. When an arm is sampled, the state of the arm is not available to the sampler. Instead, a binary signal with a known randomness that depends on the state of the arm is available. No signal is available if the arm is not sampled.
Rahul Meshram, D. Manjunath, Aditya Gopalan   +2 more
openaire   +5 more sources

Reinforcement Learning for Finite-Horizon Restless Multi-Armed Multi-Action Bandits

CoRR, 2021
We study a finite-horizon restless multi-armed bandit problem with multiple actions, dubbed R(MA)^2B. The state of each arm evolves according to a controlled Markov decision process (MDP), and the reward of pulling an arm depends on both the current state of the corresponding MDP and the action taken. The goal is to sequentially choose actions for arms
Guojun Xiong, Jian Li 0008, Rahul Singh 0001   +2 more
openaire   +2 more sources

Fairness of Exposure in Online Restless Multi-armed Bandits

International Joint Conference on Autonomous Agents and Multiagent Systems
Restless multi-armed bandits (RMABs) generalize the multi-armed bandits where each arm exhibits Markovian behavior and transitions according to their transition dynamics. Solutions to RMAB exist for both offline and online cases. However, they do not consider the distribution of pulls among the arms.
Archit Sood, Shweta Jain 0002, Sujit Gujar   +2 more
openaire   +3 more sources

Constrained Restless Bandits for Dynamic Scheduling in Cyber-Physical Systems

IEEE Access
This paper develops a sequential decision-making framework called constrained restless multi-armed bandits (CRMABs) to model problems of resource allocation under uncertainty and dynamic availability constraints.
Kesav Ram Kaza, Rahul H. Meshram, Varunkumar Mehta, Shabbir N. Merchant   +3 more
doaj   +1 more source

Equitable Restless Multi-Armed Bandits: A General Framework Inspired By Digital Health

CoRR, 2023
Restless multi-armed bandits (RMABs) are a popular framework for algorithmic decision making in sequential settings with limited resources. RMABs are increasingly being used for sensitive decisions such as in public health, treatment scheduling, anti-poaching, and -- the motivation for this work -- digital health.
Jackson A. Killian, Manish Jain, Yugang Jia, Jonathan Amar, Erich Huang, Milind Tambe   +5 more
openaire   +2 more sources

Similarity and Consistency in Algorithm‐Guided Exploration

Journal of Behavioral Decision Making, Volume 38, Issue 5, December 2025.
ABSTRACT Algorithmic advice has the potential to significantly improve human decision‐making, especially in dynamic and complex tasks that require a balance between exploration and exploitation. This study examines conditions under which individuals are willing to accept advice from algorithms in such scenarios, focusing on the interaction between ...
Ludwig Danwitz, Fabian Dvorak, Yongping Bao, Lars Hornuf, Hsuan‐Yu Lin, Sebastian Fehrler, Bettina von Helversen   +6 more
wiley   +1 more source

Leveraging AI to improve health information access in the World's largest maternal mobile health program

AI Magazine, Volume 45, Issue 4, Page 526-536, Winter 2024.
Abstract Harnessing the wide‐spread availability of cell phones, many nonprofits have launched mobile health (mHealth) programs to deliver information via voice or text to beneficiaries in underserved communities, with maternal and infant health being a key area of such mHealth programs.
Shresth Verma, Arshika Lalan, Paula Rodriguez Diaz, Panayiotis Danassis, Amrita Mahale, Kumar Madhu Sudan, Aparna Hegde, Milind Tambe, Aparna Taneja   +8 more
wiley   +1 more source

Networked Restless Multi-Arm Bandits with Reinforcement Learning

CoRR
Restless Multi-Armed Bandits (RMABs) are a powerful framework for sequential decision-making, widely applied in resource allocation and intervention optimization challenges in public health. However, traditional RMABs assume independence among arms, limiting their ability to account for interactions between individuals that can be common and ...
Hanmo Zhang, Zenghui Sun, Kai Wang 0040
openaire   +2 more sources