Pronađeno: 1-10 / 76 radova

Autori: Stankovic Srdjan S

>> Filter: Samo Article i Review

Naslov Multi-agent off-policy actor-critic algorithm for distributed multi-task reinforcement learning (Article)
Autori Stankovic Milos S  Beko Marko  Ilic Nemanja  Stankovic Srdjan S 
Info EUROPEAN JOURNAL OF CONTROL, (2023), vol. 74 br. , str. -
Projekat Fundacao para a Ciencia e a Tecnologia [7754287, UIDB/04111/2020]; Science Fund of the Republic of Serbia [7754287]; MEMS Multisensor Instrument for Aerodynamic Pressure Measurements-MEMSAERO; ECOSwarm
Ispravka ISI/Web of Science   Članak   Elečas   Rang časopisa  
Naslov Distributed consensus-based multi-agent temporal-difference learning (Article)
Autori Stankovic Milos S  Beko Marko  Stankovic Srdjan S 
Info AUTOMATICA, (2023), vol. 151 br. , str. -
Projekat Science Fund of the Republic of Serbia [6524745]; Fundacao para a Ciencia e a Tecnologia, Portugal [UIDB/04111/2020]
Ispravka ISI/Web of Science   Članak   Elečas   Rang časopisa  
Naslov Multi-Agent Actor-Critic Multitask Reinforcement Learning based on GTD(1) with Consensus (Proceedings Paper)
Autori Stankovic Milos S  Beko Marko  Ilic Nemanja  Stankovic Srdjan S 
Info 2022 IEEE 61ST CONFERENCE ON DECISION AND CONTROL (CDC), (2022), vol. br. , str. 4591-4596
Projekat Science Fund of the Republic of Serbia [6524745]; Fundacao para a Ciencia e a Tecnologia [UIDB/04111/2020]
Ispravka ISI/Web of Science   Članak  
Naslov Convergent Distributed Actor-Critic Algorithm Based on Gradient Temporal Difference (Proceedings Paper)
Autori Stankovic Milos S  Beko Marko  Stankovic Srdjan S 
Info 2022 30TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2022), (2022), vol. br. , str. 2066-2070
Projekat Science Fund of the Republic of Serbia [6524745]; Fundacao para a Ciencia e a Tecnologia [UIDB/04111/2020]
Ispravka ISI/Web of Science  
Naslov Distributed Actor-Critic Learning Using Emphatic Weightings (Proceedings Paper)
Autori Stankovic Milos S  Beko Marko  Stankovic Srdjan S 
Info 2022 8TH INTERNATIONAL CONFERENCE ON CONTROL, DECISION AND INFORMATION TECHNOLOGIES (CODIT'22), (2022), vol. br. , str. 1167-1172
Projekat Science Fund of the Republic of Serbia [6524745]; Fundacao para a Ciencia e a Tecnologia [UIDB/04111/2020]
Ispravka ISI/Web of Science   Članak   Citati: ISI/Web of Science   Scopus  
Naslov Adaptive Consensus-Based Distributed System for Multisensor Multitarget Tracking (Article)
Autori Stankovic Srdjan S  Ilic Nemanja  Stankovic Milos S 
Info IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, (2022), vol. 58 br. 3, str. 2164-2179
Projekat Science Fund of the Republic of Serbia [6524745 AI-DECIDE]
Ispravka ISI/Web of Science   Članak   Elečas   Rang časopisa   Citati: ISI/Web of Science   Scopus  
Naslov Distributed Consensus-Based Multi-Agent Off-Policy Temporal-Difference Learning (Proceedings Paper)
Autori Stankovic Milos S  Beko Marko  Stankovic Srdjan S 
Info 2021 60TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), (2021), vol. br. , str. 5976-5981
Projekat Science Fund of the Republic of Serbia [6524745]; Fundacao para a Ciencia e a Tecnologia [CEECIND/02307/2021, UIDB/04111/2020]
Ispravka ISI/Web of Science   Članak   Citati: ISI/Web of Science   Scopus  
Naslov Distributed Value Function Approximation for Collaborative Multiagent Reinforcement Learning (Article)
Autori Stankovic Milos S  Beko Marko  Stankovic Srdjan S 
Info IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS, (2021), vol. 8 br. 3, str. 1270-1280
Projekat Science Fund of the Republic of Serbia [6524745]; Fundacao para a Ciencia e a TecnologiaPortuguese Foundation for Science and TechnologyEuropean Commission [UIDB/04111/2020]
Ispravka ISI/Web of Science   Članak   Elečas   Rang časopisa   Citati: ISI/Web of Science   Scopus  
Naslov Enhancement Algorithms for Low-Light and Low-Contrast Images (Proceedings Paper)
Autori Puzovic Snezana  Petrovic Ranko  Pavlovic Milos  Stankovic Srdjan S 
Info 2020 19TH INTERNATIONAL SYMPOSIUM INFOTEH-JAHORINA (INFOTEH), (2020), vol. br. , str. -
Ispravka ISI/Web of Science  
Naslov Distributed Gradient Temporal Difference Off-policy Learning With Eligibility Traces: Weak Convergence (Proceedings Paper)
Autori Stankovic Milos S  Beko Marko  Stankovic Srdjan S 
Info IFAC PAPERSONLINE, (2020), vol. 53 br. 2, str. 1563-1568
Projekat Fundacao para a Ciencia e a TecnologiaPortuguese Foundation for Science and TechnologyEuropean Commission [IF/00325/2015, foRESTER PCIF/SSI/0102/2017, UIDB/04111/2020]
Ispravka ISI/Web of Science   Članak   Citati: ISI/Web of Science   Scopus  
Ispis zapisa u formatu:TXT | BibTeX