Tag: Reinforcement Learning

A new MAPPO-BO framework improves secondary Pinus yunnanensis forest management by coordinating harvesting and replanting decisions, increasing objective function values ...

Researchers propose a reinforcement learning method that automatically selects which layers of a pretrained neural network to fine-tune for medical ...

A new framework called TransDualKGR improves multi-hop reasoning on knowledge graphs by using a Transformer-based dynamic representation and a dual-agent ...

A two-phase optimization framework demonstrates that domain clustering governs Pareto coverage while reinforcement learning accelerates convergence during simulated drone navigation ...

In a simulated wire harness handling study, end-to-end reinforcement learning attained a 98 percent success rate, substantially outperforming multi-agent path ...

Resampling irregular clinical records into uniform time intervals distorts causal relationships and reduces reinforcement learning model performance by up to ...

A collection of research studies illustrates how artificial intelligence enhances genomic analysis across variant detection, genome assembly, and disease modeling ...

Researchers synthesize cross layer semiconductor manufacturing controls into an auditable closed loop framework balancing classical optimization with emerging intelligent systems.

Researchers have introduced SARP, a semantic-augmented reinforcement planning framework that improves mobile robot obstacle avoidance and path optimization in dynamic ...

A hierarchical attention-based reinforcement learning framework improved slice admission rates by up to 20 percent and cut resource overhead by ...

A reinforcement learning charging strategy that tracks hourly grid carbon intensity cut EV charging emissions by 1.62% while delivering identical ...

Researchers report a simulation-based explainability framework that pairs a physics-guided reinforcement learning controller with XGBoost and SHAP analysis to trace ...

A hierarchical Monte Carlo Tree Search framework with staged grid refinements improves truss design quality and cuts computational cost while ...

A new editorial collection documents how artificial intelligence is reshaping particle accelerator science, from surrogate models already in practical use ...

A simulation study reports that an AI-managed electric vehicle charging hub combining solar power, battery storage, LSTM demand forecasting and ...

A hybrid fuzzy rule-based and reinforcement learning scheduler improves real-time traffic reliability, delay, and energy use in Industrial IoT TSCH ...

A reinforcement learning framework improved bandwidth slicing in 5G-advanced O-RAN simulations, while tabular Q-learning struggled with large-state beam selection.

Researchers developed TriAlign-ATG, an AI framework that generates physically executable adversarial network traffic which evades deep-learning intrusion detectors while preserving ...

A resting-state fMRI and machine learning study identified six brain regions whose individualized dysconnectivity patterns distinguished subacute back pain patients ...

An open-source optimization framework developed with CERN has automated accelerator tuning at GSI and FAIR, cutting SIS18 injection losses from ...