Výsledky vyhledávání - Computing methodologies Machine learning Machine learning approaches Markov decision process

Exploring reinforcement learning in process control: a comprehensive survey.

Autoři: Rajasekhar, N. Radhakrishnan, T.K. Samsudeen, N.

Zdroj: International Journal of Systems Science; Oct2025, Vol. 56 Issue 14, p3528-3557, 30p

Témata: REINFORCEMENT learning, PROCESS control systems, MACHINE learning, DECISION making, ALGORITHMS, DEEP learning, INDUSTRIAL applications

Deep reinforcement learning with attention mechanisms for edge user allocation in internet of vehicles.

Autoři: Yuan, Pengtao Su, Shengchao Fu, Wenlong

Zdroj: Cluster Computing; Nov2025, Vol. 28 Issue 12, p1-20, 20p

Témata: EDGE computing, RESOURCE allocation, INTELLIGENT transportation systems, REAL-time computing, MARKOV processes, MACHINE learning, REINFORCEMENT learning

Design and Test Verification of Energy Consumption Perception AI Algorithm for Terminal Access to Smart Grid.

Autoři: Bi, Sheng Wang, Jiayan Su, Dong a další

Zdroj: Energy Engineering; 2025, Vol. 122 Issue 10, p4135-4151, 17p

Témata: ENERGY consumption, REINFORCEMENT learning, PREDICTION algorithms, MARKOV processes, MACHINE learning, ARTIFICIAL intelligence, SMART power grids, PREDICTION models

Enhancing Autonomous Driving in Urban Scenarios: A Hybrid Approach with Reinforcement Learning and Classical Control.

Autoři: Gutiérrez-Moreno, Rodrigo Barea, Rafael López-Guillén, Elena a další

Zdroj: Sensors (14248220); Jan2025, Vol. 25 Issue 1, p117, 20p

Témata: REINFORCEMENT learning, DEEP reinforcement learning, PARTIALLY observable Markov decision processes, MACHINE learning, DEEP learning

Task Offloading with LLM-Enhanced Multi-Agent Reinforcement Learning in UAV-Assisted Edge Computing.

Autoři: Zhu, Feifan Huang, Fei Yu, Yantao a další

Zdroj: Sensors (14248220); Jan2025, Vol. 25 Issue 1, p175, 19p

Témata: PARTIALLY observable Markov decision processes, DEEP reinforcement learning, LANGUAGE models, TRAJECTORY optimization, DRONE aircraft, DEEP learning

Machine learning tree trimming for faster Markov reward game solutions.

Autoři: İzgi, Burhaneddin Özkaya, Murat Üre, Nazım Kemal a další

Zdroj: Journal of Computational Science. Dec2025, Vol. 92, pN.PAG-N.PAG. 1p.

Témata: Markov processes, Machine learning, Artificial neural networks, Mathematical optimization, Decision trees, Decision making, Real-time computing, Classification

A mobility-aware task offloading approach for vehicles in cloud-edge collaborative environments.

Autoři: Guo, Feiyan Luo, Xiaoqing Liu, Xingshu a další

Zdroj: Cluster Computing; Nov2025, Vol. 28 Issue 14, p1-20, 20p

Témata: EDGE computing, RESOURCE allocation, INTELLIGENT transportation systems, URBAN transportation, MOTOR vehicles, MARKOV processes

"A Good Bot Always Knows Its Limitations": Assessing Autonomous System Decision-Making Competencies through Factorized Machine Self-Confidence.

Autoři: Israelsen, Brett Ahmed, Nisar R. Aitken, Matthew a další

Zdroj: ACM Transactions on Human-Robot Interaction; Dec2025, Vol. 14 Issue 4, p1-63, 63p

Témata: SELF-confidence, DECISION making, METACOGNITION, STATISTICAL decision making, AUTONOMOUS robots, EVALUATION methodology, MARKOV processes

Application of Optical Satellite Data in Pavement Management: Assessing Its Value in Partially Observable Stochastic Environments.

Autoři: Shahri, Mahyar Kim, Sung-Hee Sonny

Zdroj: Journal of Performance of Constructed Facilities; Aug2025, Vol. 39 Issue 4, p1-12, 12p

Témata: PAVEMENT management, MACHINE learning, PARTIALLY observable Markov decision processes, PAVEMENT testing, INFRASTRUCTURE (Economics), BOOSTING algorithms, MULTISPECTRAL imaging, REMOTE sensing

Machine Learning to Estimate Workload and Balance Resources with Live Migration and VM Placement.

Autoři: Hidayat, Taufik Ramli, Kalamullah Thereza, Nadia a další

Zdroj: Informatics; Sep2024, Vol. 11 Issue 3, p50, 15p

Témata: MACHINE learning, VIRTUAL machine systems, SUPPORT vector machines, DEEP learning, MARKOV processes, SERVER farms (Computer network management), K-nearest neighbor classification

Joint Scheduling and Placement for Vehicular Intelligent Applications Under QoS Constraints: A PPO-Based Precedence-Preserving Approach.

Autoři: Shi, Wei Chen, Bo

Zdroj: Mathematics (2227-7390); Oct2025, Vol. 13 Issue 19, p3130, 31p

Témata: SCHEDULING, REINFORCEMENT learning, MARKOV processes, REAL-time computing, MOBILE communication systems, LOAD balancing (Computer networks)

A Learning Game-Based Approach to Task-Dependent Edge Resource Allocation.

Autoři: Li, Zuopeng Ju, Hengshuai Ren, Zepeng

Zdroj: Future Internet; Dec2023, Vol. 15 Issue 12, p395, 21p

Témata: DEEP reinforcement learning, PARTIALLY observable Markov decision processes, MACHINE learning, GAMIFICATION, EDGE computing, RESOURCE allocation, REINFORCEMENT learning, GREEDY algorithms

Data-driven decision making in patient management: a systematic review.

Autoři: Lyu, Guoliang

Zdroj: BMC Medical Informatics & Decision Making; 7/1/2025, Vol. 25 Issue 1, p1-18, 18p

Témata: DECISION support systems, PATIENT decision making, INFORMATION storage & retrieval systems, ARTIFICIAL intelligence, PATIENT-centered care

Exact Decomposition Approaches for Markov Decision Processes: A Survey

Autoři: Cherki Daoui Mohammed Abbad Mohamed Tkiouat

Zdroj: Advances in Operations Research. 2010:1-19

Témata: Artificial intelligence, Learning and Inference in Bayesian Networks, Construct (python library), Variety (cybernetics), Markov chain, 0211 other engineering and technologies, Divide and conquer algorithms, 02 engineering and technology, Space (punctuation), Autonomic Computing and Self-Adaptive Systems, Component-Based Systems, Artificial Intelligence, Machine learning, FOS: Mathematics, 0202 electrical engineering, electronic engineering, information engineering, Markov process, Biology, Decomposition, Ecology, Mathematical optimization, Statistics, Computer science, Programming language, Algorithm, Operating system, FOS: Biological sciences, Computer Science, Physical Sciences, Software Reliability Assessment and Prediction, Markov decision process, State space, Software, Mathematics

Enhanced PV power prediction using LSTM-integrated soft actor–critic model based on long short-term memory.

Autoři: Xu, Yang Lu, Zhengqiu

Zdroj: Journal of Computational Methods in Sciences & Engineering; Sep2025, Vol. 25 Issue 5, p4774-4786, 13p

Témata: REINFORCEMENT learning, DEEP reinforcement learning, LONG short-term memory, MARKOV processes, ELECTRIC power distribution grids, DEEP learning

A Software-Defined Networking-Based Computing-Aware Routing Path Selection Method.

Autoři: Lv, Chang Cao, Xianzhi Li, Jiali a další

Zdroj: Electronics (2079-9292); Nov2025, Vol. 14 Issue 22, p4418, 21p

Témata: SOFTWARE-defined networking, REINFORCEMENT learning, EDGE computing, NETWORK routing protocols, RESOURCE allocation, DISTRIBUTED computing, CLOUD computing, MARKOV processes

Multi-agent deep reinforcement learning for integrated production and maintenance optimisation in shared manufacturing.

Autoři: Peng, Xiaoshuai Wang, Shiyi Wang, Kangzhou

Zdroj: International Journal of Production Research; Dec2025, Vol. 63 Issue 23, p8761-8780, 20p

Témata: REINFORCEMENT learning, PRODUCTION planning, SIMULATION methods & models, RESOURCE allocation, MULTIAGENT systems, PROCESS optimization, COMPUTER integrated manufacturing systems, MARKOV processes

Optimizing Attention and Cognitive Control Costs Using Temporally Layered Architectures.

Autoři: Patel, Devdhar Sejnowski, Terrence Siegelmann, Hava

Zdroj: Neural Computation; Dec2024, Vol. 36 Issue 12, p2734-2763, 30p

Témata: MACHINE learning, ATTENTION control, COGNITIVE ability, COST control, MARKOV processes

Optimized task assignment and predictive maintenance for industrial machines using Markov decision process.

Autoři: Nasir, Ali Mekid, Samir Sawlan, Zaid a další

Zdroj: Operational Research; Dec2025, Vol. 25 Issue 4, p1-31, 31p

Mean-Field Multiagent Reinforcement Learning: A Decentralized Network Approach.

Autoři: Gu, Haotian Guo, Xin Wei, Xiaoli a další

Zdroj: Mathematics of Operations Research; Feb2025, Vol. 50 Issue 1, p506-536, 31p

Témata: MACHINE learning, REINFORCEMENT learning, MARL, PROBABILITY measures, MARKOV processes