Suchergebnisse - "Reinforcement Learning Algorithms"

A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems

Autoren: Rafael Figueiredo Prudencio Marcos R. O. A. Máximo Esther Luna Colombini

Quelle: IEEE Transactions on Neural Networks and Learning Systems. 35:10237-10257

Schlagwörter: FOS: Computer and information sciences, Computer Science - Machine Learning, Artificial intelligence, Class (philosophy), Computer Science - Artificial Intelligence, Robot, Massive Open Online Courses, Reinforcement Learning Algorithms, Perspective (graphical), Social Sciences, Machine Learning (stat.ML), 02 engineering and technology, 01 natural sciences, Social psychology, Machine Learning (cs.LG), Data science, Deep Learning, Statistics - Machine Learning, Artificial Intelligence, Field (mathematics), Reinforcement learning, Machine learning, 0202 electrical engineering, electronic engineering, information engineering, FOS: Mathematics, Psychology, Biology, Applied Psychology, 0105 earth and related environmental sciences, Human–computer interaction, Botany, Pure mathematics, Robotics, Taxonomy (biology), Reinforcement Learning, Computer science, Learning Analytics, Computer Science Applications, FOS: Psychology, World Wide Web, Popularity, Artificial Intelligence (cs.AI), Online Learning, Computer Science, Physical Sciences, Open research, Educational Data Mining and Learning Analytics, Digital Mental Health Interventions and Efficacy, Mathematics

Zugangs-URL: https://pubmed.ncbi.nlm.nih.gov/37030754
http://arxiv.org/abs/2203.01387

A hybrid multi-agent deep actor-critic learning and particle swarm optimization algorithm for active voltage control in smart grids with renewable energies

Autoren: Elham Nazari Negar Nazari Samaneh Hosseini Semnani et al.

Quelle: e-Prime: Advances in Electrical Engineering, Electronics and Energy, Vol 13, Iss , Pp 101075- (2025)

Schlagwörter: Multi-agent reinforcement learning algorithms, Particle swarm optimization, Power grid, Active voltage control, Renewable energies, Electrical engineering. Electronics. Nuclear engineering, TK1-9971

Dateibeschreibung: electronic resource

Relation: http://www.sciencedirect.com/science/article/pii/S2772671125001822; https://doaj.org/toc/2772-6711

Zugangs-URL: https://doaj.org/article/0be1bfeec0ec40b9bbe85bb170f9cda4

Runtime Verification of Learning Properties for Reinforcement Learning Algorithms

Autoren: Mannucci, T. Filho, J. De Oliveira DSS - Defence, Safety & Security et al.

Weitere Verfasser: Mannucci, T. Filho, J. De Oliveira DSS - Defence, Safety & Security et al.

Quelle: Electronic Proceedings in Theoretical Computer Science. 395:205-219

Schlagwörter: FOS: Computer and information sciences, Computer Science - Machine Learning, Trial and error, Verification properties, Property, Learning phasis, Reinforcement learning algorithms, Learning algorithms, Verification techniques, Machine Learning (cs.LG), Physical systems, Run-time verification, Design steps, Reinforcement learning, Systems operation

Zugangs-URL: http://arxiv.org/abs/2311.09811
https://resolver.tno.nl/uuid:775c8fd0-fe24-4fbe-ae49-ffe9501e58de
https://publications.tno.nl/publication/34641925/OikPO1/mannucci-2023-runtime.pdf

Deep Reinforcement Learning for Autonomous Navigation on Duckietown Platform: Evaluation of Adversarial Robustness

Autoren: Hosseini, Abdullah Houti, Saeid Qadir, Junaid

Quelle: 2023 International Symposium on Networks, Computers and Communications (ISNCC). :1-6

Schlagwörter: Learning systems, Perturbation techniques, Complex environments, Autonomous vehicles, Security of data, Driving environment, Deep learning, Reinforcement learning algorithms, Learning algorithms, Automobile drivers, Control system synthesis, End to end, Reinforcement learnings, Transportation industry, Reinforcement learning, Autonomous driving, Security risks, Open systems, Autonomous navigation, Decision making, Reinforcement learning systems

Dateibeschreibung: application/pdf

Zugangs-URL: https://hdl.handle.net/10576/66069

Research on data transmission based on DDPG algorithm

Autoren: Yan Danting Jiao Xinquan

Quelle: Dianzi Jishu Yingyong, Vol 51, Iss 1, Pp 0-0 (2025)

Schlagwörter: reliable transmission, ddpg algorithm, TK7800-8360, Electronics, data transmission, deep reinforcement learning algorithms, fpga, gigabit ethernet

Zugangs-URL: https://doaj.org/article/a92a7accc4364bea9abdedba734f10df

On the Sample Complexity of Representation Learning in Multi-Task Bandits with Global and Local Structure

Autoren: Russo, Alessio Proutiere, Alexandre

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence. :9658-9667

Schlagwörter: ML: Representation Learning, ML: Online Learning & Bandits, ML: Reinforcement Learning Algorithms, ML: Reinforcement Learning Theory, Mathematical Statistics, Matematisk statistik, Electrical Engineering, Elektro- och systemteknik, Datalogi, Computer Science

Dateibeschreibung: print

Zugangs-URL: https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-333761
https://doi.org/10.1609/aaai.v37i8.26155

Deep reinforcement learning-driven decision support system design for precision agriculture: optimizing farming and resource use

Autoren: BAI, QINGSHAN

Quelle: Turkish Journal of Agriculture and Forestry

Schlagwörter: Deep reinforcement learning, intelligent agricultural vehicles, path planning, reinforcement learning algorithms, deep neural networks, Agriculture, Forest Sciences

Dateibeschreibung: application/pdf

Relation: https://journals.tubitak.gov.tr/agriculture/vol49/iss3/12; https://journals.tubitak.gov.tr/context/agriculture/article/3289/viewcontent/Deep_20reinforcement_20learning_driven_20decision_20support_20system_20design_20for_20precision.pdf

Verfügbarkeit: https://journals.tubitak.gov.tr/agriculture/vol49/iss3/12
https://doi.org/10.55730/1300-011X.3289
https://journals.tubitak.gov.tr/context/agriculture/article/3289/viewcontent/Deep_20reinforcement_20learning_driven_20decision_20support_20system_20design_20for_20precision.pdf

Dynamic warning zone and a short-distance goal for autonomous robot navigation using deep reinforcement learning

Autoren: Estrella Montero Husna Mutahira Nabih Pico et al.

Quelle: Complex & Intelligent Systems, Vol 10, Iss 1, Pp 1149-1166 (2023)

Schlagwörter: Artificial intelligence, 0209 industrial biotechnology, Robot, Reinforcement Learning Algorithms, FOS: Mechanical engineering, Ocean Engineering, Information technology, Modeling Pedestrian Dynamics and Evacuations, 02 engineering and technology, 7. Clean energy, Pedestrian Dynamics, Engineering, Dynamic obstacle avoidance, Artificial Intelligence, Autonomous robots, Reinforcement learning, Mobile robot, 11. Sustainability, Dynamic warning zone, 0202 electrical engineering, electronic engineering, information engineering, 10. No inequality, Robot control, Deep reinforcement learning, Behavior-based robotics, Human–computer interaction, 4. Education, QA75.5-76.95, Robotics, 15. Life on land, T58.5-58.64, Reinforcement Learning, Computer science, 3. Good health, Electronic computers. Computer science, Social robot, Automotive Engineering, Physical Sciences, Computer Science, Autonomous Vehicle Technology and Safety Systems, Lane Detection, Robot learning, Short-distance goal, Simulation

Zugangs-URL: https://doaj.org/article/76ff0d3c05fc4fb6afa5abaddc9cc5b7

A Two-Stage Multi-Objective Evolutionary Reinforcement Learning Framework for Continuous Robot Control

Autoren: Hai-Long Tran L. Doan Ngoc Hoang Luong et al.

Quelle: Proceedings of the Genetic and Evolutionary Computation Conference. :577-585

Schlagwörter: Artificial intelligence, Metric (unit), Robot, Robustness (evolution), Reinforcement Learning Algorithms, Evolutionary computation, Biochemistry, Gene, Context (archaeology), Engineering, Artificial Intelligence, Evolutionary algorithm, Reinforcement learning, Machine learning, FOS: Mathematics, Biology, Geography, Multi-Objective Optimization, Mathematical optimization, Paleontology, Reinforcement Learning, Computer science, Multi-objective optimization, Chemistry, Operations management, Computational Theory and Mathematics, Particle Swarm Optimization, Application of Genetic Programming in Machine Learning, Computer Science, Physical Sciences, Evolutionary Algorithms, Benchmark (surveying), Multiobjective Optimization in Evolutionary Algorithms, Pareto principle, Mathematics, Geodesy

Offline Pre-trained Multi-agent Decision Transformer

Autoren: Linghui Meng Muning Wen Chenyang Le et al.

Quelle: Machine Intelligence Research. 20:233-248

Schlagwörter: Artificial intelligence, Marl, Reinforcement Learning Algorithms, Generalization, Offline learning, Mathematical analysis, 7. Clean energy, decision making, Learning with Noisy Labels in Machine Learning, Multi-Agent Systems, Systems engineering, Task (project management), Engineering, Artificial Intelligence, Meta-Learning, Reinforcement learning, Machine learning, FOS: Mathematics, 14. Life underwater, Biology, Transformer, 4. Education, multi-agent reinforcement learning (MARL), Paleontology, Voltage, Pre-training model, 15. Life on land, Reinforcement Learning, Computer science, Structural basin, Operating system, Multimedia, Online learning, Application of Genetic Programming in Machine Learning, Electrical engineering, Computer Science, Physical Sciences, transformer, Online and offline, offline reinforcement learning, Mathematics, Robust Learning

Zugangs-URL: https://discovery-pp.ucl.ac.uk/id/eprint/10168378/

2D LiDAR Based Reinforcement Learning for Multi-Target Path Planning in Unknown Environment

Autoren: Nasr Abdalmanan Kamarulzaman Kamarudin Muhammad Aizat Abu Bakar et al.

Quelle: IEEE Access, Vol 11, Pp 35541-35555 (2023)

Schlagwörter: Artificial intelligence, Biomechanics of Bipedal Locomotion in Robots and Animals, Path Planning, Robot, RL, Biomedical Engineering, Reinforcement Learning Algorithms, Kinodynamic Planning, FOS: Medical engineering, mobile robot, Sampling-Based Motion Planning Algorithms, Probabilistic Roadmaps, Engineering, Artificial Intelligence, Reinforcement learning, Mobile robot, path planning, Real-Time Planning, Lidar, Geography, Obstacle, Path (computing), Remote sensing, 15. Life on land, Obstacle avoidance, Reinforcement Learning, Computer science, TK1-9971, Programming language, Archaeology, Computer Science, Physical Sciences, Q-learning, Motion planning, Computer vision, Electrical engineering. Electronics. Nuclear engineering, Computer Vision and Pattern Recognition, Benchmark (surveying), Geodesy

Zugangs-URL: https://doaj.org/article/4e54233bf52e4f299bc41e9b8041560a

On the Training of Reinforcement Learning-based Algorithms in 5G and Beyond Radio Access Networks

Autoren: Vilà Muñoz, Irene Pérez Romero, Jordi Sallent Roig, Oriol

Quelle: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)

Schlagwörter: Training 5G mobile communication systems, 0301 basic medicine, 0303 health sciences, Wireless communications, Learning strategy, Algorithmic solutions, Radio access networks, Reinforcement learning algorithms, Work-flows, Xarxes locals sense fil Wi-Fi, Learning-based algorithms, Reinforcement Learning, Radio, Wireless communication systems, Reinforcement learnings, 03 medical and health sciences, Comunicació sense fil, Sistemes de, Machine learning, Reinforcement learning, Radio Access Network, Àrees temàtiques de la UPC::Enginyeria de la telecomunicació, Machine-learning, Network slicing

Dateibeschreibung: application/pdf

Zugangs-URL: https://hdl.handle.net/2117/380800
https://doi.org/10.1109/netsoft54395.2022.9844032

Safe Reinforcement Learning using Data-Driven Predictive Control

Autoren: Mahmoud Selim Amr Alanwar M. Watheq El‐Kharashi et al.

Quelle: 2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA). :1-6

Schlagwörter: FOS: Computer and information sciences, Computer Science - Machine Learning, Artificial intelligence, 0209 industrial biotechnology, Robot, Action (physics), Robot Navigation, Reinforcement Learning Algorithms, FOS: Mechanical engineering, Set (abstract data type), Control (management), Systems and Control (eess.SY), 02 engineering and technology, Electrical Engineering and Systems Science - Systems and Control, Sampling-Based Motion Planning Algorithms, Quantum mechanics, Machine Learning (cs.LG), Computer Science - Robotics, Engineering, Artificial Intelligence, Reinforcement learning, State (computer science), Machine learning, FOS: Electrical engineering, electronic engineering, information engineering, Software deployment, Model predictive control, Biology, Real-Time Planning, Physics, Controller (irrigation), Reachability, Robotics, Reinforcement Learning, Computer science, Agronomy, Programming language, Algorithm, Operating system, Aerospace engineering, Computer Science, Physical Sciences, Automotive Engineering, Computer Vision and Pattern Recognition, Autonomous Vehicle Technology and Safety Systems, Intersection (aeronautics), Robotics (cs.RO), Lane Detection

Zugangs-URL: http://arxiv.org/abs/2211.11027

A Survey on Distributed Reinforcement Learning

Autoren: Maroning Useng Suleiman Avdulrahman

Quelle: Mesopotamian Journal of Big Data. 2022:44-50

Schlagwörter: Artificial intelligence, Scale (ratio), Computer Networks and Communications, Variety (cybernetics), Reinforcement Learning Algorithms, Workload, Quantum mechanics, 7. Clean energy, Data science, Database, 0508 media and communications, Artificial Intelligence, Computer security, Reinforcement learning, Machine learning, Key (lock), 10. No inequality, Geography, Internet of Things and Edge Computing, Physics, 4. Education, 05 social sciences, Scalability, Crowdsourcing for Research and Data Collection, Reinforcement Learning, Computer science, Computer Science Applications, Operating system, Computer Science, Physical Sciences, Benchmark (surveying), Geodesy

Low Dimensional State Representation Learning with Robotics Priors in Continuous Action Spaces

Autoren: Botteghi, N. Alaa, K. Poel, M. et al.

Quelle: IEEE International Conference on Intelligent Robots and Systems. :190-197

Schlagwörter: Mobile robots, Reinforcement learning, Robotics, Virtual reality, Action spaces, Continuous actions, End to end, High-dimensional, Low dimensional, Real-world, Reinforcement learning algorithms, Reinforcement learning solution, Robotic tasks, State representation, Learning algorithms

Dateibeschreibung: print

Zugangs-URL: https://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-55968
https://doi.org/10.1109/IROS51168.2021.9635936

Offline motion libraries and online MPC for advanced mobility skills

Autoren: Marko Bjelonic Ruben Grandia Moritz Geilinger et al.

Quelle: The International Journal of Robotics Research, 41 (9–10)

Schlagwörter: Artificial intelligence, 0209 industrial biotechnology, Biomechanics of Bipedal Locomotion in Robots and Animals, model predictive control, Robot, Astronomy, Biomedical Engineering, Reinforcement Learning Algorithms, Trajectory, Geometry, Control (management), 02 engineering and technology, FOS: Medical engineering, Sampling-Based Motion Planning Algorithms, Probabilistic Roadmaps, Time horizon, Systems engineering, Task (project management), Engineering, Artificial Intelligence, Online algorithm, Control theory (sociology), FOS: Mathematics, Control of Locomotion, Online model, Model predictive control, trajectory optimization, Real-Time Planning, robotics, Motion (physics), Physics, wheeled and legged locomotion, Horizon, Mathematical optimization, Statistics, offline motion library, Reinforcement Learning, Computer science, Optimal Motion Planning, Algorithm, Operating system, Trajectory optimization, Physical Sciences, Computer Science, Computation, Online and offline, Computer Vision and Pattern Recognition, Mathematics

Dateibeschreibung: application/application/pdf

Zugangs-URL: http://hdl.handle.net/20.500.11850/551315

Offline Decentralized Multi-Agent Reinforcement Learning

Autoren: Jiechuan Jiang Zongqing Lu

Quelle: Frontiers in Artificial Intelligence and Applications ISBN: 9781643684369

Schlagwörter: Exploit, FOS: Computer and information sciences, Computer Science - Machine Learning, Artificial intelligence, 0209 industrial biotechnology, Computer Networks and Communications, Reinforcement Learning Algorithms, Normalization (sociology), 02 engineering and technology, Biochemistry, Gene, Multi-Agent Systems, Machine Learning (cs.LG), Value (mathematics), Sociology, Artificial Intelligence, Distributed Multi-Agent Coordination and Control, Distributed Optimization, Computer security, Reinforcement learning, Machine learning, Computer Science - Multiagent Systems, Simulation to Real-world Transfer, Reinforcement Learning, Computer science, FOS: Sociology, Chemistry, Transition (genetics), Computational Theory and Mathematics, Online Learning, Anthropology, Computer Science, Physical Sciences, Adaptive Dynamic Programming for Optimal Control, Multiagent Systems (cs.MA)

Zugangs-URL: http://arxiv.org/abs/2108.01832

Intrinsic Motivations and Planning to Explain Tool-Use Development: A Study With a Simulated Robot Model

Autoren: Kristsana Seepanomwan Daniele Caligiore Kevin J O'Regan et al.

Weitere Verfasser: Kristsana Seepanomwan Daniele Caligiore Kevin J O'Regan et al.

Quelle: IEEE Transactions on Cognitive and Developmental Systems (2020). doi:10.1109/TCDS.2020.2986411
info:cnr-pdr/source/autori:Kristsana Seepanomwan; Daniele Caligiore; Kevin J. O'Regan; Gianluca Baldassarre/titolo:Intrinsic Motivations and Planning to Explain Tool-Use Development: A Study with a Simulated Robot Model/doi:10.1109%2FTCDS.2020.2986411/rivista:IEEE Transactions on Cognitive and Developmental Systems/anno:2020/pagina_da:/pagina_a:/intervallo_pagine:/volume

Schlagwörter: reinforcement learning, Social Interaction with Robots, Artificial intelligence, Social Psychology, Robot, Economics, Reinforcement Learning Algorithms, Social Sciences, Developmental robotics, Humanoid robot, embodied cognitive development, Tools, Task (project management), 03 medical and health sciences, 0302 clinical medicine, Artificial Intelligence, simulated iCub humanoid robot, goal generation and intrinsic motivations (IMs), Machine learning, Developmental and Educational Psychology, Infant Understanding, Psychology, 0501 psychology and cognitive sciences, affordances and planning, Development of Theory of Mind in Children, Human–computer interaction, Human Perception of Robots, [INFO.INFO-RB] Computer Science [cs]/Robotics [cs.RO], 05 social sciences, Computational modeling, Robotics, neural networks, Computer science, Management, FOS: Psychology, Toy manufacturing industry, Planning, dynamic movement primitives (DMPs), Task analysis, Computer Science, Physical Sciences, task analysis, Robots, development of tool use

Dateibeschreibung: application/pdf

Zugangs-URL: https://ieeexplore.ieee.org/ielx7/7274989/7422051/09103030.pdf
https://ieeexplore.ieee.org/document/9103030/
https://hdl.handle.net/20.500.14243/377806
https://ieeexplore.ieee.org/ielx7/7274989/9732511/09103030.pdf
https://doi.org/10.1109/TCDS.2020.2986411
https://u-paris.hal.science/hal-03671558v1/document
https://doi.org/10.1109/tcds.2020.2986411
https://u-paris.hal.science/hal-03671558v1

Multiagent Reinforcement Learning for Strategic Decision Making and Control in Robotic Soccer Through Self-Play

Autoren: Bruno Brandao Telma Woerle De Lima Anderson da Silva Soares et al.

Quelle: IEEE Access, Vol 10, Pp 72628-72642 (2022)

Schlagwörter: reinforcement learning, Artificial intelligence, Robot, multi-agent, Reinforcement Learning Algorithms, Social Sciences, Heuristic, Control (management), self-play, 02 engineering and technology, Management Science and Operations Research, Mechanism Design in Auctions and Procurement Contracts, Multi-Agent Systems, Decision Sciences, Artificial Intelligence, Reinforcement learning, 0202 electrical engineering, electronic engineering, information engineering, Biology, Ecology, Competition (biology), Robotics, Reinforcement Learning, Computer science, TK1-9971, Application of Genetic Programming in Machine Learning, FOS: Biological sciences, Computer Science, Physical Sciences, Electrical engineering. Electronics. Nuclear engineering, strategy, Decision making

Zugangs-URL: https://doaj.org/article/938f5c022fab48289b3a7b30e860c599

Systematic Data-Driven Continual Self-Learning

Autoren: Corcoran, Diarmuid Boman, Magnus, Professor Latré, Steven, Professor

Weitere Verfasser: Corcoran, Diarmuid Boman, Magnus, Professor Latré, Steven, Professor

Quelle: TRITA-EECS-AVL.

Schlagwörter: Data-Driven Methods, Self-Learning Systems, Reinforcement Learning Algorithms, Implementation Architectures, Datadrivna metoder, Självlärande system, Reinforcement Learning-algoritmer, Implementeringsarkitekturer

Dateibeschreibung: electronic

Zugangs-URL: https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-325733
https://kth.diva-portal.org/smash/get/diva2:1750762/FULLTEXT02.pdf