dc.contributor.author | Sarıgül, Mehmet | |
dc.contributor.author | Avcı, Mutlu | |
dc.date.accessioned | 12.07.201910:50:10 | |
dc.date.accessioned | 2019-07-12T22:06:22Z | |
dc.date.available | 12.07.201910:50:10 | |
dc.date.available | 2019-07-12T22:06:22Z | |
dc.date.issued | 2018 | |
dc.identifier.citation | Sarıgül, M., Avcı, M. (2018). Q Learning Regression Neural Network. Neural Network World, 28(5), 415–431.
https://doi.org/10.14311/NNW.2018.28.023 | en_US |
dc.identifier.issn | 1210-0552 | |
dc.identifier.uri | https://doi.org/10.14311/NNW.2018.28.023 | |
dc.identifier.uri | https://hdl.handle.net/20.500.12508/702 | |
dc.description | WOS: 000449440400001 | en_US |
dc.description.abstract | In this work, a Nadaraya-Watson kernel based learning system which owns general regression neural network topology is adapted to Q learning method to evaluate a quick and efficient action selection policy for reinforcement learning problems. By means of the proposed method Q value function is generalized and learning speed of Q agent is accelerated. The training data of the developed neural network are obtained by a standard Q learning agent on closed-loop simulation system. The efficiency of the proposed method is tested on popular reinforcement learning benchmarks and its performance is compared with other popular regression methods and Q-learning utilized methods. QLRNN increased the learning performance and it learns faster than other methods on selected benchmarks. Test results showed the efficiency and the importance of the proposed network. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Neural Network World | en_US |
dc.relation.isversionof | 10.14311/NNW.2018.28.023 | en_US |
dc.rights | info:eu-repo/semantics/openAccess | en_US |
dc.subject | Reinforcement learning | en_US |
dc.subject | Q learning | en_US |
dc.subject | Q value function approximation | en_US |
dc.subject | General regression neural network | en_US |
dc.subject | Kernel based regression | en_US |
dc.subject.classification | Computer Science | en_US |
dc.subject.classification | Artificial Intelligence | en_US |
dc.subject.other | Reınforcement | en_US |
dc.subject.other | Temperature | en_US |
dc.subject.other | Model | en_US |
dc.title | Q Learning Regression Neural Network | en_US |
dc.type | article | en_US |
dc.relation.journal | Neural Network World | en_US |
dc.contributor.department | Mühendislik ve Doğa Bilimleri Fakültesi -- Bilgisayar Mühendisliği Bölümü | en_US |
dc.contributor.authorID | 0000-0001-7323-6864 | en_US |
dc.identifier.volume | 28 | en_US |
dc.identifier.issue | 5 | en_US |
dc.identifier.startpage | 415 | en_US |
dc.identifier.endpage | 431 | en_US |
dc.relation.publicationcategory | Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı | en_US |
dc.contributor.isteauthor | Sarıgül, Mehmet | en_US |
dc.relation.index | Web of Science Core Collection - Science Citation Index Expanded | en_US |