Contextual Multi-Armed Bandit With Costly Feature Observation in Non-Stationary Environments

Maximizing long-term rewards is the primary goal in sequential decision-making problems. The majority of existing methods assume that side information is freely available, enabling the learning agent to observe all features' states before making a decision. In real-world problems, however...

Full description

Bibliographic Details

Published in:	IEEE Open Journal of Signal Processing
Main Authors:	Saeed Ghoorchian, Evgenii Kortukov, Setareh Maghsudi
Format:	Article
Language:	English
Published:	IEEE 2024-01-01
Subjects:	Contextual multi-armed bandit non-stationary process online learning costly information acquisition
Online Access:	https://ieeexplore.ieee.org/document/10502231/