reinforcement learning

Learning Subject Tags from Incomplete Labels: A Recall-Oriented VLM Pipeline for Historical Photographs

Assigning subject tags to photographs is essential for access and discovery in digital libraries, yet doing it by hand does not scale. Vision–language models (VLMs) are a powerful and increasingly popular tool for such tasks, but prompting them to generate open-vocabulary subject tags directly yields unsatisfactory res...

AI-RLWHF: AI-assisted reinforcement learning with honesty and feedback

AI-RLWHF is an open, experimentation-first workspace for Transformer Lab plugins and reinforcement learning workflows that reward honesty, feedback capture and multi-model collaboration. It began as a research spinoff of Knowledge3D.

ALGORITHMIC BARGAINING: A DYNAMIC PRICING MODEL FOR PRODUCTS AND SERVICES ACROSS ONLINE PLATFORMS

This article presents a comprehensive study of algorithmic bargaining within dynamic pricing systems, focusing on its usability, challenges, and broader market implications.Algorithmic bargaining, increasingly used in industries such as e-commerce, retail, and transportation, allows companies to dynamically adjust pric...

Multi-centre cutting service composition in cloud manufacturing: a hierarchical decision model with guillotine cutting evaluation

In material-intensive Cloud Manufacturing (CMfg), traditional Service Composition and Optimal Selection (SCOS) approaches often treat cutting services as abstract functional units, which may lead to biased cost estimation and infeasible assignments. This study proposes a hierarchical decision-aid model named DiCACE to...

From coordination to selective intervention: an on-demand coordination method for adaptive traffic signal control, dynamic speed regulation, and route guidance

Coordinating multiple traffic interventions does not necessarily lead to safer or more efficient traffic operations, because redundant or poorly timed interventions may introduce additional disturbances. This study moves beyond the conventional focus on how multiple interventions should cooperate by formulating coordin...

Emergent collaborative scheduling in satellite swarms: A distributed multi-agent reinforcement learning approach with adaptive experience evolution

Comparison and Contrast of two Machine Learning Assisted In-Device Scheduling Applications

Managing offloaded tasks efficiently is vital for keeping devices fast and responsive. The main hurdle is finding a way to schedule and run these incoming workloads without starving local applications of critical CPU, RAM, and energy. This study evaluates how Federated Learning (FL) and Reinforcement Learning (RL) can...

Reinforcement learning-assisted mean-line design for axial compressor repeating stages

Code and tutorials for: A general method for estimating reliability using Bayesian Measurement Uncertainty

R and Stan code for the simulation studies, applied example and tutorials accompanying the preprint A general method for estimating reliability using Bayesian Measurement Uncertainty (Bignardi, Kievit & Bürkner). Relative measurement uncertainty (RMU) estimates reliability by drawing pairs of samples from each subject'...

Task-Adaptive Reinforcement Learning for Unified OCR in Maritime and Complex Documents

Maritime logistics relies on documents that combine dense multilingual text, irregular layouts, and task-specific output schemas, requiring operational systems to recover text, structure, location, and semantics. We trained Hi-Dolphin-OCRusing a task-adaptive reinforcement-learning framework that formulates text spotti...

Integrated transcriptomics and machine learning reveal core genes associated with Bacillus safensis-mediated resistance to tomato bacterial wilt

Abstract Background Bacterial wilt (BW), caused by Ralstonia pseudosolanacearum , is one of the most destructive diseases of tomato, yet the molecular mechanisms underlying biological control remain poorly understood. Results This study investigated the protective effects of Bacillus safensis strain H23 using physiolog...

Mission-Oriented Four-Dimensional UAV Trajectory Planning with Reinforcement Learning

Supporting simulation data for “Mission-Oriented Four-Dimensional UAV Trajectory Planning with Reinforcement Learning”. The dataset includes per-task evaluation records for four planning methods on 200 shared test missions, CPA-feature ablation records, training-reward scalars, representative four-dimensional trajector...