Cover Image

Relaxed Indexability and Index Policy for Partially Observable Restless Bandits

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Liu, Keqin
Format:	Preprint
Published:	2021
Subjects:	Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Lagrangian Relaxation for Multi-Action Partially Observable Restless Bandits: Heuristic Policies and Indexability
by: Meshram, Rahul, et al.
Published: (2025)

Low-Complexity Algorithm for Restless Bandits with Imperfect Observations
by: Liu, Keqin, et al.
Published: (2021)

Lagrangian Index Policy for Restless Bandits with Average Reward
by: Avrachenkov, Konstantin, et al.
Published: (2024)

Model Predictive Control is Almost Optimal for Restless Bandit
by: Gast, Nicolas, et al.
Published: (2024)

DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback
by: Xiong, Guojun, et al.
Published: (2024)

Efficient Algorithm Design of Dynamic Spectrum Access by Whittle Index
by: Liu, Keqin, et al.
Published: (2024)

Model Predictive Control is almost Optimal for Heterogeneous Restless Multi-armed Bandits
by: Narasimha, Dheeraj, et al.
Published: (2025)

Stochastic Differential Dynamic Programming for Trajectory Optimization under Partial Observability
by: Fujiwara, Masahiro, et al.
Published: (2026)

Stochastic Optimal Feedforward-Feedback Control for Partially Observable Sensorimotor Systems
by: Berret, Bastien, et al.
Published: (2026)

LP Relaxations for Routing and Wavelength Assignment with Partial Path Protection: Formulations and Computations
by: Yang, Xianyan, et al.
Published: (2025)

Wasserstein Distributionally Robust Control and State Estimation for Partially Observable Linear Systems
by: Jang, Minhyuk, et al.
Published: (2024)

Finite-Horizon Partially Observable Semi-Markov Games with Risk Probability Criteria
by: Wen, Xin, et al.
Published: (2025)

Adversarial Decision-Making in Partially Observable Multi-Agent Systems: A Sequential Hypothesis Testing Approach
by: Zhou, Haosheng, et al.
Published: (2025)

Sensitivity of Filter Kernels and Robustness Bounds to Transition and Measurement Kernel Perturbations in Partially Observable Stochastic Control
by: Demirci, Yunus Emre, et al.
Published: (2025)

General Formulation and PCL-Analysis for Restless Bandits with Limited Observability
by: Liu, Keqin, et al.
Published: (2023)

Restless Bandits with Average Reward: Breaking the Uniform Global Attractor Assumption
by: Hong, Yige, et al.
Published: (2023)

On Borkar and Young Relaxed Control Topologies and Continuous Dependence of Invariant Measures on Control Policy
by: Yüksel, Serdar
Published: (2023)

Optimal Denial-of-Service Attacks Against Partially-Observable Real-Time Monitoring Systems
by: Kriouile, Saad, et al.
Published: (2024)

Learning Over-Relaxation Policies for ADMM with Convergence Guarantees
by: Lin, Junan, et al.
Published: (2026)

Weakly-Coupled Multi-Action Restless Bandits -- Exponential Convergence in Probability
by: Fu, Jing, et al.
Published: (2026)

A Restless Bandit Model for Dynamic Ride Matching with Reneging Travelers
by: Fu, Jing, et al.
Published: (2021)

Bayesian Dissuasion with Bandit Exploration
by: DAntoni, Massimo, et al.
Published: (2024)

MIP Relaxations in Factorable Programming
by: He, Taotao, et al.
Published: (2023)

Observability of linear systems on the Heisenberg Lie group
by: Cavalheiro, Thiago Matheus, et al.
Published: (2025)

Constrained Average-Reward Intermittently Observable MDPs
by: Avrachenkov, Konstantin, et al.
Published: (2025)

A Tight SDP Relaxation for the Cubic-Quartic Regularization Problem
by: Zhou, Jinling, et al.
Published: (2025)

Adversarial Observability and Performance Trade-offs in Optimal Control
by: Fotiadis, Filippos, et al.
Published: (2025)

Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior
by: Cui, Kai, et al.
Published: (2023)

Computing Control Lyapunov-Barrier Functions: Softmax Relaxation and Smooth Patching with Formal Guarantees
by: Liu, Jun, et al.
Published: (2025)

Scalable Bi-causal Optimal Transport via KL Relaxation and Policy Gradients
by: Cao, Haoyang, et al.
Published: (2026)

Centering ADMM for the Semidefinite Relaxation of the QAP
by: Kanoh, Shin-ichi, et al.
Published: (2020)

On the Strength of Linear Relaxations in Ordered Optimization
by: Blanco, Víctor, et al.
Published: (2025)

Relax-and-Cut for Temporal SCUC Decomposition
by: Xiong, Jinxin, et al.
Published: (2025)

Relaxation methods for pessimistic bilevel optimization
by: Benchouk, Imane, et al.
Published: (2024)

Achieving Exponential Asymptotic Optimality in Average-Reward Restless Bandits without Global Attractor Assumption
by: Hong, Yige, et al.
Published: (2024)

Solving the train-platforming problem via a two-level Lagrangian Relaxation approach
by: Zhang, Qin, et al.
Published: (2024)

Learning to Sparsify Stochastic Linear Bandits
by: Wang, Zhengmiao, et al.
Published: (2026)

Augmenting Subspace Optimization Methods with Linear Bandits
by: Menickelly, Matt
Published: (2024)

Controllability and Observability Imply Exponential Decay of Sensitivity in Dynamic Optimization
by: Shin, Sungho, et al.
Published: (2021)

Characterizing Controllability and Observability for Systems with Locality, Communication, and Actuation Constraints
by: Conger, Lauren, et al.
Published: (2024)