Eylem Seç
Adaptive Dynamic Programming with Eligibility Traces and Complexity Reduction of High-Dimensional Systems
Başlık:
Adaptive Dynamic Programming with Eligibility Traces and Complexity Reduction of High-Dimensional Systems
Yazar:
Al-Dabooni, Seaar Jawad Kadhim, author.
ISBN:
9780438111042
Yazar Ek Girişi:
Fiziksel Tanımlama:
1 electronic resource (372 pages)
Genel Not:
Source: Dissertation Abstracts International, Volume: 79-11(E), Section: B.
Advisors: Donald C. Wunsch Committee members: Cihan Dagli; Jagannathan Sarangapani; R. Joe Stanley; Maciej Zawodniok.
Özet:
This dissertation investigates the application of a variety of computational intelligence techniques, particularly clustering and adaptive dynamic programming (ADP) designs especially heuristic dynamic programming (HDP) and dual heuristic programming (DHP). Moreover, a one-step temporal-difference (TD(0)) and n-step TD (TD(lambda)) with their gradients are utilized as learning algorithms to train and online-adapt the families of ADP. The dissertation is organized into seven papers. The first paper demonstrates the robustness of model order reduction (MOR) for simulating complex dynamical systems. Agglomerative hierarchical clustering based on performance evaluation is introduced for MOR. This method computes the reduced order denominator of the transfer function by clustering system poles in a hierarchical dendrogram. Several numerical examples of reducing techniques are taken from the literature to compare with our work. In the second paper, a HDP is combined with the Dyna algorithm for path planning. The third paper uses DHP with an eligibility trace parameter (lambda) to track a reference trajectory under uncertainties for a nonholonomic mobile robot by using a first-order Sugeno fuzzy neural network structure for the critic and actor networks. In the fourth and fifth papers, a stability analysis for a model-free action-dependent HDP(lambda) is demonstrated with batch- and online-implementation learning, respectively. The sixth work combines two different gradient prediction levels of critic networks. In this work, we provide a convergence proofs. The seventh paper develops a two-hybrid recurrent fuzzy neural network structures for both critic and actor networks. They use a novel n-step gradient temporal-difference (gradient of TD(lambda)) of an advanced ADP algorithm called value-gradient learning (VGL(lambda)), and convergence proofs are given. Furthermore, the seventh paper is the first to combine the single network adaptive critic with VGL(lambda).
Notlar:
School code: 0587
Tüzel Kişi Ek Girişi:
Mevcut:*
Yer Numarası | Demirbaş Numarası | Shelf Location | Lokasyon / Statüsü / İade Tarihi |
---|---|---|---|
XX(688265.1) | 688265-1001 | Proquest E-Tez Koleksiyonu | Arıyor... |
On Order
Liste seç
Bunu varsayılan liste yap.
Öğeler başarıyla eklendi
Öğeler eklenirken hata oldu. Lütfen tekrar deneyiniz.
:
Select An Item
Data usage warning: You will receive one text message for each title you selected.
Standard text messaging rates apply.