Results 131 to 140 of about 492,986 (210)

The AI‑driven evolution of dynamic pricing: a semi‑systematic review and novel hierarchical classification

Applied Operations and Analytics
Dynamic pricing (DP) has become a central strategy for revenue management in the data-driven economy, supported by rapid advances in machine learning, reinforcement learning, and algorithmic optimization.
Zahra Fasihi, Mohammad Rezaei-Pandari, Fattaneh Torkaman, Mohammadreza Razzazi   +3 more
doaj   +1 more source

Design of a personalized recommendation system for ideological and political education using reinforcement learning

Discover Artificial Intelligence
This paper proposes a personalised recommendation system for Ideological and Political Education using Reinforcement Learning techniques. The primary objective is to create a dynamic, adaptable learning system that provides content tailored to individual
Zhiyong Li
doaj   +1 more source

Closed-loop cognitive state control: a hypothesis framework for real-time estimation, stabilization, and recovery of task-specific high-performance cognitive states

Frontiers in Neuroergonomics
Human performance often fails not because latent capacity is absent, but because access to high-functioning cognitive states is unstable under fatigue, distraction, overload, and pressure.
Ibrahim Mourad
doaj   +1 more source

Provably and Practically Efficient Neural Contextual Bandits

, 2022
We consider the neural contextual bandit problem. In contrast to the existing work which primarily focuses on ReLU neural nets, we consider a general set of smooth activation functions.
Zhao, Qing, Vakili, Sattar, Salgia, Sudeep   +2 more
core  

Toward Specialized Wireless Networks Using an ML-Driven Radio Interface

IEEE Access
Future wireless networks will need to support diverse applications (such as extended reality), scenarios (such as fully automated industries), and technological advances (such as terahertz communications).
Kamil Szczech, Maksymilian Wojnar, Katarzyna Kosek-Szott, Krzysztof Rusek, Szymon Szott, Dileepa Marasinghe, Nandana Rajatheva, Richard Combes, Francesc Wilhelmi, Anders Jonsson, Boris Bellalta   +10 more
doaj   +1 more source

Cooperate or Not Cooperate: Transfer Learning With Multi-Armed Bandit for Spatial Reuse in Wi-Fi

IEEE Transactions on Machine Learning in Communications and Networking
The exponential increase in the demand for high-performance services such as streaming video and gaming by wireless devices has posed several challenges for Wireless Local Area Networks (WLANs).
Pedro Enrique Iturria-Rivera, Marcel Chenier, Bernard Herscovici, Burak Kantarci, Melike Erol-Kantarci   +4 more
doaj   +1 more source

Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles

, 2021
A fundamental challenge in contextual bandits is to develop flexible, general-purpose algorithms with computational requirements no worse than classical supervised learning tasks such as classification and regression.
Rakhlin, Alexander, Foster, Dylan J
core  

Intelligent EMS Dispatch via Adaptive Learning With Counterfactual and Risk-Aware Optimization

IEEE Access
Emergency Medical Services (EMS) dispatch demands real-time decisions under uncertainty, requiring simultaneous optimization of response speed, spatial equity, and system resilience.
Wuttipong Kumwilaisak
doaj   +1 more source

Contextual Multinomial Logit Bandits with General Value Functions

Contextual multinomial logit (MNL) bandits capture many real-world assortment recommendation problems such as online retailing/advertising. However, prior work has only considered (generalized) linear value functions, which greatly limits its ...
Zhang, Mengxiao, Luo, Haipeng
core