Výsledky vyhledávání - "PPO algorithm"

Aerial Combat Maneuver Decision Method for Unmanned Aerial Vehicles Based on Deep Reinforcement Learning

Autoři: ZHANG Xiangrui, TAN Tai, LI Hui, ZHANG Jianwei, LI Bowen

Zdroj: Jisuanji gongcheng, Vol 51, Iss 12, Pp 324-336 (2025)

Témata: unmanned aerial vehicle (uav), proximal policy optimization (ppo) algorithm, six degrees of freedom, dual reward (dr), hierarchical framework, Computer engineering. Computer hardware, TK7885-7895, Computer software, QA76.75-76.765

Popis souboru: electronic resource

Relation: https://www.ecice06.com/fileup/1000-3428/PDF/20251230.pdf; https://doaj.org/toc/1000-3428

Přístupová URL adresa: https://doaj.org/article/07fd5ad5932e4c72afbc0653c696dba3

LSTM-PPO-Based Dynamic Scheduling Optimization for High-Speed Railways Under Blizzard Conditions

Autoři: Na Wang Zhiyuan Cai Yinzhen Li

Zdroj: Systems, Vol 13, Iss 10, p 884 (2025)

Témata: railway transportation, dynamic scheduling for high-speed railways, LSTM-PPO algorithm, blizzard conditions, delay propagation, multi-objective optimization, Systems engineering, TA168, Technology (General), T1-995

Popis souboru: electronic resource

Relation: https://www.mdpi.com/2079-8954/13/10/884; https://doaj.org/toc/2079-8954

Přístupová URL adresa: https://doaj.org/article/e7bb462b83a6449f8aacd7ab2407f146

Research on Multi-Objective Optimization Models for Intersection Crossing of Connected Autonomous Vehicles With Traffic Signals

Autoři: Xiaobin Ning Haoran Tian Yong Lin a další

Zdroj: IEEE Access, Vol 12, Pp 36825-36840 (2024)

Témata: 0209 industrial biotechnology, multi-objective optimization, PPO algorithm, traffic light intersection control, 0502 economics and business, 05 social sciences, 11. Sustainability, intelligent traffic system, optimal speed planning, Electrical engineering. Electronics. Nuclear engineering, 02 engineering and technology, Connected autonomous vehicles, TK1-9971

Přístupová URL adresa: https://doaj.org/article/555e3247d21b4757a2d8dd6aaa19b318

A low-carbon optimization scheduling method of CIES based on PPO algorithm

Autoři: CHEN Fan WU Lingxiao WANG Man a další

Zdroj: 电力工程技术, Vol 43, Iss 6, Pp 88-99 (2024)

Témata: community integrated energy system (cies), optimize scheduling, proximal policy optimization (ppo) algorithm, ladder-type carbon trading mechanism, penalty coefficient, carbon emission, Applications of electric power, TK4001-4102

Popis souboru: electronic resource

Relation: https://www.epet-info.com/dlgcjsen/article/abstract/240411338; https://doaj.org/toc/2096-3203

Přístupová URL adresa: https://doaj.org/article/eacfd2ea293a488a8d59af10035bf26a

A Time-Driven Dynamic Weapon Target Assignment Method

Autoři: Chang Liu Jiang Li Ye Wang a další

Zdroj: IEEE Access, Vol 11, Pp 129623-129639 (2023)

Témata: reinforcement learning, Dynamic weapon target assignment, PPO algorithm, simulation model, heuristic algorithm, Electrical engineering. Electronics. Nuclear engineering, TK1-9971

Přístupová URL adresa: https://doaj.org/article/6f2327ac2b284ef6941af86059d9bed1

Adaptive Algorithm for Selecting the Optimal Trading Strategy Based on Reinforcement Learning for Managing a Hedge Fund

Autoři: B. Belyakov D. Sizykh

Zdroj: IEEE Access, Vol 12, Pp 189047-189063 (2024)

Témata: Algorithmic trading, artificial intelligence, deep reinforcement learning, hedge fund management, optimal trading strategy, proximal policy optimization (PPO) algorithm, Electrical engineering. Electronics. Nuclear engineering, TK1-9971

Popis souboru: electronic resource

Relation: https://ieeexplore.ieee.org/document/10792442/; https://doaj.org/toc/2169-3536

Přístupová URL adresa: https://doaj.org/article/72b2addbcf6d41f7bb907b6dd0f5c066

FMI real-time co-simulation-based machine deep learning control of HVAC systems in smart buildings: Digital-twins technology

Autoři: Saeid-Reza Mohseni Meisam Jahanshahi Zeitouni Ahmad Parvaresh a další

Zdroj: Mohseni, S-R, Jahanshahi Zeitouni, M, Parvaresh, A, Abrazeh, S, Gheisarnejad Chirani, M & Khooban, M H 2023, 'FMI real-time co-simulation-based machine deep learning control of HVAC systems in smart buildings : Digital-twins technology', Transactions of the Institute of Measurement and Control, vol. 45, no. 4, pp. 661-673. https://doi.org/10.1177/01423312221119635

Témata: HVAC system, 0209 industrial biotechnology, hardware-in-loop, PPO algorithm, digital twin (DT), nonsingular terminal sliding-mode controller, 02 engineering and technology, 7. Clean energy

Přístupová URL adresa: https://pure.au.dk/portal/en/publications/7fa49ffc-1985-41cd-913e-50a786191f42
https://doi.org/10.1177/01423312221119635

Fast Frequency Control Strategy Based on Worst-Case Network Attack Perception

Autoři: Wentao Xu Zhenghang Song Peiyuan Guan

Zdroj: Mathematics, Vol 13, Iss 1, p 132 (2024)

Témata: voltage source converters, frequency control, worst-case PPO algorithm, worst attacks, smart grids, Mathematics, QA1-939

Popis souboru: electronic resource

Relation: https://www.mdpi.com/2227-7390/13/1/132; https://doaj.org/toc/2227-7390

Přístupová URL adresa: https://doaj.org/article/5fad337236eb433ba43d2e3ee9c478de

A Deep-Reinforcement-Learning-Based Digital Twin for Manufacturing Process Optimization

Autoři: Abdelmoula Khdoudi Tawfik Masrour Ibtissam El Hassani a další

Zdroj: Systems, Vol 12, Iss 2, p 38 (2024)

Témata: digital twin, smart manufacturing, deep reinforcement learning, twin delayed DDPG algorithm, PPO algorithm, manufacturing process optimization, Systems engineering, TA168, Technology (General), T1-995

Relation: https://www.mdpi.com/2079-8954/12/2/38; https://doaj.org/toc/2079-8954; https://doaj.org/article/31ca2694304146da8950366ddfa5075f

Dostupnost: https://doi.org/10.3390/systems12020038
https://doaj.org/article/31ca2694304146da8950366ddfa5075f

Research on Behavioral Decision at an Unsignalized Roundabout for Automatic Driving Based on Proximal Policy Optimization Algorithm

Autoři: Jingpeng Gan Jiancheng Zhang Yuansheng Liu

Zdroj: Applied Sciences, Vol 14, Iss 7, p 2889 (2024)

Témata: autonomous vehicle, deep reinforcement learning, optimized PPO algorithm, unsignalized roundabout, gap acceptance theory, Technology, Engineering (General). Civil engineering (General), TA1-2040, Biology (General), QH301-705.5, Physics, QC1-999, Chemistry, QD1-999

Relation: https://www.mdpi.com/2076-3417/14/7/2889; https://doaj.org/toc/2076-3417; https://doaj.org/article/3147b64605354ccd9cc86e06039bdec7

Dostupnost: https://doi.org/10.3390/app14072889
https://doaj.org/article/3147b64605354ccd9cc86e06039bdec7

Local Path Planning of Robot Based on Improved PPO Algorithm

Autoři: LIU Guoming, LI Caihong, LI Yongdi, ZHANG Guosheng, ZHANG Yaoyu, GAO Tengteng

Zdroj: Jisuanji gongcheng, Vol 49, Iss 2, Pp 119-126,135 (2023)

Témata: robot, local path planning, long short-term memory(lstm) neural network, proximal policy optimization(ppo) algorithm, virtual target point, Computer engineering. Computer hardware, TK7885-7895, Computer software, QA76.75-76.765

Popis souboru: electronic resource

Relation: https://www.ecice06.com/fileup/1000-3428/PDF/20230215.pdf; https://doaj.org/toc/1000-3428

Přístupová URL adresa: https://doaj.org/article/22f2c935e57f49398574375d69fc4704

Design of a Hyper-Casual Futsal Mobile Game Using a Machine-Learned AI Agent-Player

Autoři: Hyeyoung An Jungyoon Kim

Zdroj: Applied Sciences, Vol 13, Iss 4, p 2071 (2023)

Témata: mobile devices, futsal, digital game, hyper-casual, machine learning, PPO algorithm, Technology, Engineering (General). Civil engineering (General), TA1-2040, Biology (General), QH301-705.5, Physics, QC1-999, Chemistry, QD1-999

Relation: https://www.mdpi.com/2076-3417/13/4/2071; https://doaj.org/toc/2076-3417; https://doaj.org/article/c3ff2cae55944be89dbef9fe393c9682

Dostupnost: https://doi.org/10.3390/app13042071
https://doaj.org/article/c3ff2cae55944be89dbef9fe393c9682

Multi-UAV Cooperative Offensive Combat Intelligent Planning Based on Deep Reinforcement Learning

Autoři: LI Junsheng YUE Longfei ZUO Jialiang a další

Zdroj: Hangkong gongcheng jinzhan, Vol 13, Iss 6, Pp 40-49,96 (2022)

Témata: multi-uav, deep learning, deep reinforcement learning, ppo algorithm, generalization, cooperative combat, Motor vehicles. Aeronautics. Astronautics, TL1-4050

Popis souboru: electronic resource

Relation: http://hkgcjz.cnjournals.com/hkgcjz/article/abstract/2022017?st=article_issue; https://doaj.org/toc/1674-8190

Přístupová URL adresa: https://doaj.org/article/29999897dae141a18b53245a57d017e5

Active flow control in simulations of fluid flows based on deep reinforcement learning

Autoři: Darshan Thummar

Témata: Active flow control, Flow around 2D cylinder, open-loop and closed-loop control, Deep reinforcement learning, Proximal policy optimization (PPO) algorithm

Relation: https://zenodo.org/records/4897961; oai:zenodo.org:4897961; https://doi.org/10.5281/zenodo.4897961

Dostupnost: https://doi.org/10.5281/zenodo.4897961
https://zenodo.org/records/4897961

Active flow control in simulations of fluid flows based on deep reinforcement learning

Autoři: Thummar, Darshan

Témata: Deep reinforcement learning, open-loop and closed-loop control, Flow around 2D cylinder, Active flow control, Proximal policy optimization (PPO) algorithm

Razvoj programskog agenta-igrača za računalnu igru primjenom podržanog učenja

Autoři: Tadić, Bartul Popović, Siniša

Přispěvatelé: Tadić, Bartul Popović, Siniša

Témata: Podržano učenje, machine learning, Unity, PPO algorithm, deep neural networks, TECHNICAL SCIENCES. Computing, TEHNIČKE ZNANOSTI. Računarstvo, Reinforcement learning, ML-Agents Toolkit, PPO algoritam, duboke neuronske mreže, strojno učenje

Popis souboru: application/pdf

Přístupová URL adresa: https://repozitorij.fer.unizg.hr/islandora/object/fer:11013
https://urn.nsk.hr/urn:nbn:hr:168:774527
https://repozitorij.fer.unizg.hr/islandora/object/fer:11013/datastream/PDF

Evoluční algoritmy v posilovaném učení ; Evolutionary Algorithms in Reinforcement Learning

Autoři: Gulčíková, Sabína Sekanina, Lukáš Vašíček, Zdeněk

Přispěvatelé: Gulčíková, Sabína Sekanina, Lukáš Vašíček, Zdeněk

Témata: posilované učenie, evolučné výpočty, evolučné posilované učenie, evolučný dizajn hodnotiaceho signálu, DQN algoritmus, PPO algoritmus, CartPole úloha, generalizácia, reinforcement learning, evolutionary computation, reward shaping, evolutionary reward design, DQN algorithm, PPO algorithm, CartPole task, generalization

Popis souboru: application/pdf; text/html

Relation: GULČÍKOVÁ, S. Evoluční algoritmy v posilovaném učení [online]. Brno: Vysoké učení technické v Brně. Fakulta informačních technologií. 2025.; 165202; https://hdl.handle.net/11012/255136

Dostupnost: https://hdl.handle.net/11012/255136

Evaluación de rendimiento de arquitecturas paralelas y de propósito específico para el aprendizaje por refuerzo en juegos ; Performance evaluation of parallel and specic-purpose architectures for reinforcement learning in games

Autoři: Guzmán Muñoz, Javier Igual Peña, Francisco Daniel Costero Valero, Luis Mª

Přispěvatelé: Guzmán Muñoz, Javier Igual Peña, Francisco Daniel Costero Valero, Luis Mª

Témata: 004(043.3), Aprendizaje por refuerzo, Algoritmo PPO, Red neuronal de convoluci´on, Ray RLlib, Entornos Gym, TPU Google Coral, Aceleradores hardware, Reinforcement learning, PPO algorithm, Convolutional neural network, Gym environ- ments, Google Coral TPU, Hardware accelerators, Informática (Informática), 1203.17 Informática

Popis souboru: application/pdf

Relation: https://hdl.handle.net/20.500.14352/10496

Dostupnost: https://hdl.handle.net/20.500.14352/10496

Evaluación de rendimiento de arquitecturas paralelas y de propósito específico para el aprendizaje por refuerzo en juegos

Autoři: Guzmán Muñoz, Javier Igual Peña, Francisco Costero Valero, Luis Mª a další

Přispěvatelé: Guzmán Muñoz, Javier Igual Peña, Francisco Costero Valero, Luis Mª a další

Zdroj: E-Prints Complutense. Archivo Institucional de la UCM
instname
E-Prints Complutense: Archivo Institucional de la UCM
Universidad Complutense de Madrid
Docta Complutense

Témata: Informática, Informática (Informática), Entornos Gym, Ray RLlib, Convolutional neural network, Red neuronal de convoluci´on, Google Coral TPU, TPU Google Coral, PPO algorithm, Aprendizaje por refuerzo, Algoritmo PPO, Reinforcement learning, Hardware accelerators, 1203.17 Informática, 004(043.3), Aceleradores hardware, Gym environ- ments

Popis souboru: application/pdf

Přístupová URL adresa: https://hdl.handle.net/20.500.14352/10496

Razvoj programskog agenta-igrača za računalnu igru primjenom podržanog učenja ; Development of a software agent-player for a computer game using reinforcement learning

Autoři: Tadić, Bartul Popović, Siniša

Přispěvatelé: Tadić, Bartul Popović, Siniša

Témata: Podržano učenje, ML-Agents Toolkit, strojno učenje, PPO algoritam, duboke neuronske mreže, Unity, Reinforcement learning, machine learning, PPO algorithm, deep neural networks, TEHNIČKE ZNANOSTI. Računarstvo, TECHNICAL SCIENCES. Computing

Popis souboru: application/pdf

Relation: https://zir.nsk.hr/islandora/object/fer:11013; https://urn.nsk.hr/urn:nbn:hr:168:774527; https://repozitorij.unizg.hr/islandora/object/fer:11013; https://repozitorij.unizg.hr/islandora/object/fer:11013/datastream/PDF

Dostupnost: https://zir.nsk.hr/islandora/object/fer:11013
https://urn.nsk.hr/urn:nbn:hr:168:774527
https://repozitorij.unizg.hr/islandora/object/fer:11013
https://repozitorij.unizg.hr/islandora/object/fer:11013/datastream/PDF