Reinforcement learning algorithms

Basit Öğe Kaydı
dc.authorscopusidWadhah Zeyad Tareq / 56543609600
dc.authorwosidWadhah Zeyad Tareq / GLS-2101-2022
dc.contributor.authorTareq, Wadhah Zeyad
dc.contributor.authorAmasyalı, Mehmet Fatih
dc.date.accessioned2025-04-18T09:59:58Z
dc.date.available2025-04-18T09:59:58Z
dc.date.issued2024
dc.departmentİstinye Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü
dc.description.abstractThe training scheme is a critical fundamental in multiagent systems, especially with reinforcement learning methods. The reinforcement learning agent builds its experience through interacting with the environment by trial and error. Later, the agent uses these experiences to decide which is the correct action and which one is not. In multiagent systems, two or more agents learn through trial and error in the same environment. These agents can cooperate to perform a single task or to compete to achieve a single goal. The training of multiple agents has many challenges. Selecting a suitable training scheme is one of these challenges. This chapter examines different schemes to find out the optimal scheme for training multiagent deep reinforcement learning. All applied schemes concentrated on two main fundamentals: centralized and distributed. All schemes tested on self-driving filed with multiple autonomous vehicles. Different traffic scenarios are utilized to measure the impact of each scheme in different situations. In the experiments, three different schemes were tested: centralized, distributed, and hybrid. The results show that the combined model (hybrid) achieves better performance compared with standard models.
dc.identifier.citationTareq, W. Z. T., & Amasyalı, M. F. (2024). Reinforcement learning algorithms. In Decision-Making Models (pp. 339-350). Academic Press.
dc.identifier.doi10.1016/B978-0-443-16147-6.00007-4
dc.identifier.endpage350
dc.identifier.isbn978-044316148-3
dc.identifier.isbn978-044316147-6
dc.identifier.scopus2-s2.0-85202803611
dc.identifier.startpage339
dc.identifier.urihttp://dx.doi.org/10.1016/B978-0-443-16147-6.00007-4
dc.identifier.urihttps://hdl.handle.net/20.500.12713/6911
dc.indekslendigikaynakScopus
dc.institutionauthorTareq, Wadhah Zeyad
dc.institutionauthoridWadhah Zeyad Tareq / 0000-0003-4571-0295
dc.language.isoen
dc.publisherElsevier
dc.relation.ispartofDecision-making models: a perspective of fuzzy logic and machine learning
dc.relation.publicationcategoryKitap Bölümü - Uluslararası
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectDeep Reinforcement Learning
dc.subjectHighway-Env
dc.subjectMultiAgent
dc.subjectReinforcement Learning
dc.titleReinforcement learning algorithms
dc.typeBook Chapter

Dosyalar

Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Bilgisayar Mühendisliği Bölümü Kitap Bölümü Koleksiyonu