Results 51 to 60 of about 497,803 (209)
Reward-driven hallucination control in retrieval-augmented generation via bandit learning [PDF]
Retrieval-Augmented Generation (RAG) grounds large language model responses in externally retrieved evidence, but many RAG systems use a fixed generation strategy for all queries.
Aggarwal Shaurya +3 more
doaj +1 more source
Battery-aided privacy preservation of household electricity load profiles under time-of-use tariffs
Collecting fine-grained data on electricity usage can reduce the user’s energy cost by accurate demand response and improve the services from utilities. However, non-intrusive power load monitoring (NILM) technology shows that these data will reveal the ...
Mao Zhu, Xi Luo, Zhiyi Li, Can Wan
doaj +1 more source
Multi‐Agent Reinforcement Learning for Joint Police Patrol and Dispatch
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
Contextual Bandit Approaches to Personalized Tutoring
In order to choose an algorithm to recommend student tutoring in the ASSISTments platform, a simulator was created based on historical ASSISTments data. Various contextual bandit models were tested in that simulator.
Healy, Alan
core +2 more sources
Network Latency Estimation for Telesurgery Using Deep Reinforcement Learning
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
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
Detection of District Heating Pipe Network Leakage Fault Using UCB Arm Selection Method
District heating networks make up an important public energy service, in which leakage is the main problem affecting the safety of pipeline network operation. This paper proposes a Leakage Fault Detection (LFD) method based on the Linear Upper Confidence
Yachen Shen +5 more
doaj +1 more source
LLMs-augmented Contextual Bandit
Contextual bandits have emerged as a cornerstone in reinforcement learning, enabling systems to make decisions with partial feedback. However, as contexts grow in complexity, traditional bandit algorithms can face challenges in adequately capturing and utilizing such contexts. In this paper, we propose a novel integration of large language models (LLMs)
Ali Baheri, Cecilia O. Alm
openaire +2 more sources
Flexible job shop scheduling problem with combined processing constraint is a common scheduling problem in assembly manufacturing industry. However, traditional methods for classic flexible job shop scheduling problem (FJSP) cannot be directly applied ...
Haihua Zhu +3 more
doaj +1 more source
ABSTRACT The British army in India took great care to provide European troops with facilities for sexual relations while anxiously managing venereal disease. Examining archival evidence, political debates and medical discourse from the nineteenth century, this article examines the colonial military enterprise of regulated prostitution in colonial ...
Sameera Chauhan
wiley +1 more source

