English
Related papers

Related papers: Indexability and Rollout Policy for Multi-State Pa…

200 papers

This paper studies the off-policy evaluation problem, where one aims to estimate the value of a target policy based on a sample of observations collected by another policy. We first consider the multi-armed bandit case, establish a minimax…

Artificial Intelligence · Computer Science 2014-09-15 Lihong Li , Remi Munos , Csaba Szepesvari

We study the Lagrangian Index Policy (LIP) for restless multi-armed bandits with long-run average reward. In particular, we compare the performance of LIP with the performance of the Whittle Index Policy (WIP), both heuristic policies known…

Machine Learning · Computer Science 2026-01-01 Konstantin Avrachenkov , Vivek S. Borkar , Pratik Shah

We study decision making in environments where the reward is only partially observed, but can be modeled as a function of an action and an observed context. This setting, known as contextual bandits, encompasses a wide variety of…

Machine Learning · Computer Science 2011-05-09 Miroslav Dudik , John Langford , Lihong Li

An extension of the traditional two-armed bandit problem is considered, in which the decision maker has access to some side information before deciding which arm to pull. At each time t, before making a selection, the decision maker is able…

Information Theory · Computer Science 2007-07-16 Chih-Chun Wang , Sanjeev R. Kulkarni , H. Vincent Poor

This paper studies multi-stage systems with end-to-end bandit feedback. In such systems, each job needs to go through multiple stages, each managed by a different agent, before generating an outcome. Each agent can only control its own…

Machine Learning · Computer Science 2024-08-20 I-Hong Hou

We study high-dimensional multi-armed contextual bandits with batched feedback where the $T$ steps of online interactions are divided into $L$ batches. In specific, each batch collects data according to a policy that depends on previous…

Machine Learning · Statistics 2023-11-27 Jianqing Fan , Zhaoran Wang , Zhuoran Yang , Chenlu Ye

In the classic multi-armed bandits problem, the goal is to have a policy for dynamically operating arms that each yield stochastic rewards with unknown means. The key metric of interest is regret, defined as the gap between the expected…

Optimization and Control · Mathematics 2010-11-23 Yi Gai , Bhaskar Krishnamachari , Rahul Jain

Policies for Partially Observable Markov Decision Processes (POMDPs) are often designed using a nominal system model. In practice, this model can deviate from the true system during deployment due to factors such as calibration drift or…

Artificial Intelligence · Computer Science 2026-04-24 Benjamin Kraske , Qi Heng Ho , Federico Rossi , Morteza Lahijanian , Zachary Sunberg

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,…

Machine Learning · Computer Science 2024-02-12 Archit Sood , Shweta Jain , Sujit Gujar

We propose a novel approach for planning agents to compose abstract skills via observing and learning from historical interactions with the world. Our framework operates in a Markov state-space model via a set of actions under unknown…

Artificial Intelligence · Computer Science 2022-07-19 Tin Lai

Motivated by emerging applications such as live-streaming e-commerce, promotions and recommendations, we introduce and solve a general class of non-stationary multi-armed bandit problems that have the following two features: (i) the…

Machine Learning · Statistics 2021-12-23 David Simchi-Levi , Zeyu Zheng , Feng Zhu

We consider a non stationary multi-armed bandit in which the population preferences are positively and negatively reinforced by the observed rewards. The objective of the algorithm is to shape the population preferences to maximize the…

Machine Learning · Computer Science 2024-03-04 Viraj Nadkarni , D. Manjunath , Sharayu Moharir

We consider a multi-channel opportunistic communication system where the states of these channels evolve as independent and statistically identical Markov chains (the Gilbert-Elliot channel model). A user chooses one channel to sense and…

Networking and Internet Architecture · Computer Science 2016-11-17 Qing Zhao , Bhaskar Krishnamachari , Keqin Liu

Determining what experience to generate to best facilitate learning (i.e. exploration) is one of the distinguishing features and open challenges in reinforcement learning. The advent of distributed agents that interact with parallel…

Machine Learning · Computer Science 2019-12-17 Tom Schaul , Diana Borsa , David Ding , David Szepesvari , Georg Ostrovski , Will Dabney , Simon Osindero

Taking advantage of contextual information can potentially boost the performance of recommender systems. In the era of big data, such side information often has several dimensions. Thus, developing decision-making algorithms to cope with…

Machine Learning · Computer Science 2023-07-26 Saeed Ghoorchian , Evgenii Kortukov , Setareh Maghsudi

We introduce robustness in \textit{restless multi-armed bandits} (RMABs), a popular model for constrained resource allocation among independent stochastic processes (arms). Nearly all RMAB techniques assume stochastic dynamics are precisely…

Machine Learning · Computer Science 2022-06-23 Jackson A. Killian , Lily Xu , Arpita Biswas , Milind Tambe

Most learning to rank research has assumed that the utility of different documents is independent, which results in learned ranking functions that return redundant results. The few approaches that avoid this have rather unsatisfyingly…

Machine Learning · Computer Science 2012-09-04 Aleksandrs Slivkins , Filip Radlinski , Sreenivas Gollapudi

LLMs are increasingly used to design reward functions based on human preferences in Reinforcement Learning (RL). We focus on LLM-designed rewards for Restless Multi-Armed Bandits, a framework for allocating limited resources among agents.…

Machine Learning · Computer Science 2025-10-22 Shresth Verma , Niclas Boehmer , Lingkai Kong , Milind Tambe

Time-constrained decision processes have been ubiquitous in many fundamental applications in physics, biology and computer science. Recently, restart strategies have gained significant attention for boosting the efficiency of…

Machine Learning · Computer Science 2020-07-02 Semih Cayci , Atilla Eryilmaz , R. Srikant

Partially observable Markov decision processes (POMDPs) are a general framework for sequential decision-making under latent state uncertainty, yet learning in POMDPs is intractable in the worst case. Motivated by sensing and probing…

Machine Learning · Computer Science 2026-01-27 Ming Shi , Yingbin Liang , Ness B. Shroff
‹ Prev 1 8 9 10 Next ›