Results 51 to 60 of about 492,986 (210)
, 2021 Contextual bandits algorithms have become essential in real-world user interaction problems in recent years. However, these algorithms represent context as attribute value representation, which makes them infeasible for real world domains like social ...
Ravindran, Balaraman +2 more
core +1 more source
Label-Efficient Automatic Modulation Recognition Using Contextual Bandits
IEEE AccessDeep-learning-based automatic modulation recognition (AMR) requires labeled data that can be costly to obtain. This paper presents a label-efficient framework combining a convolutional neural network with a two-action LinUCB contextual bandit for ...
Mehmet Hakan Durak
doaj +1 more source
British Educational Research Journal, EarlyView.Abstract The global teacher shortage continues to intensify, with disparate impacts across geographic and socio‐economic communities. In Queensland, Australia, where this study originates, post‐COVID teacher shortages have intensified workforce pressures, leaving several regional, rural and remote schools as some of the ‘hardest‐to‐staff’ in the ...
Matthew Readette +5 more
wiley +1 more source
CBRAP: Contextual Bandits with RAndom Projection
, 2017 Contextual bandits with linear payoffs, which are also known as linear bandits, provide a powerful alternative for solving practical problems of sequential decisions, e.g., online advertisements.
King, Irwin +5 more
core +1 more source
State‐Dependent Market (In)Efficiency in Cryptocurrency Markets
Journal of Futures Markets, EarlyView.ABSTRACT This paper develops a meta‐learning framework to test whether cryptocurrency market inefficiency is static or state‐dependent. To resolve competing claims between the Efficient and Adaptive Market Hypotheses (AMH), we construct an adaptive trading strategy using high‐frequency data for 50 major cryptocurrencies.
Sasan Barak +2 more
wiley +1 more source
Adaptive Noise Exploration for Neural Contextual Multi-Armed Bandits
AlgorithmsIn contextual multi-armed bandits, the relationship between contextual information and rewards is typically unknown, complicating the trade-off between exploration and exploitation.
Chi Wang, Lin Shi, Junru Luo
doaj +1 more source
Multi‐Agent Reinforcement Learning for Joint Police Patrol and Dispatch
Naval Research Logistics (NRL), EarlyView.ABSTRACT Police patrol units need to split their time between performing preventive patrol and being dispatched to serve emergency incidents. In the existing literature, patrol and dispatch decisions are often studied separately. We consider joint optimization of these two decisions to improve police operations efficiency and reduce response time to ...
Matthew Repasky, He Wang, Yao Xie
wiley +1 more source
HD-CB: The First Exploration of Hyperdimensional Computing for Contextual Bandits Problems
IEEE Open Journal of the Computer SocietyHyperdimensional Computing (HDC), or Vector Symbolic Architectures, is a computing paradigm that combines symbolic reasoning with the efficiency of distributed representations.
M. Angioli +5 more
doaj +1 more source
Network Latency Estimation for Telesurgery Using Deep Reinforcement Learning
SmartBot, EarlyView.Overview of the proposed two‐stage deep reinforcement learning framework for network latency prediction in telesurgery. The pipeline includes data collection from simulated catheter navigation sessions (Philippines–Botswana), feature engineering, DQN‐based direction prediction (85.8% accuracy), direction‐to‐value transformation, and value forecasting ...
Bakang Kgopolo +2 more
wiley +1 more source
Estimation Considerations in Contextual Bandits
CoRR, 2017 Contextual bandit algorithms are sensitive to the estimation method of the outcome model as well as the exploration method used, particularly in the presence of rich heterogeneity or complex outcome models, which can lead to difficult estimation problems along the path of learning. We study a consideration for the exploration vs. exploitation framework
Dimakopoulou, Maria +3 more
openaire +3 more sources