Quantum Inspired Algorithms for Learning and Control of Stochastic Systems
Başlık:
Quantum Inspired Algorithms for Learning and Control of Stochastic Systems
Yazar:
Rajagopal, Karthikeyan, author.
ISBN:
9780438120709
Yazar Ek Girişi:
Fiziksel Tanımlama:
1 electronic resource (124 pages)
Genel Not:
Source: Dissertation Abstracts International, Volume: 79-11(E), Section: B.
Advisors: Balakrishnan Sivasubramanya Nadar Committee members: Jerome Busemeyer; Robert G. Landers; Ming Leu; Jagannathan Sarangapani.
Özet:
Motivated by the limitations of the current reinforcement learning and optimal control techniques, this dissertation proposes quantum theory inspired algorithms for learning and control of both single-agent and multi-agent stochastic systems.
A common problem encountered in traditional reinforcement learning techniques is the exploration-exploitation trade-off. To address the above issue an action selection procedure inspired by a quantum search algorithm called Grover's iteration is developed. This procedure does not require an explicit design parameter to specify the relative frequency of explorative/exploitative actions.
The second part of this dissertation extends the powerful adaptive critic design methodology to solve finite horizon stochastic optimal control problems. To numerically solve the stochastic Hamilton Jacobi Bellman equation, which characterizes the optimal expected cost function, large number of trajectory samples are required. The proposed methodology overcomes the above difficulty by using the path integral control formulation to adaptively sample trajectories of importance.
The third part of this dissertation presents two quantum inspired coordination models to dynamically assign targets to agents operating in a stochastic environment. The first approach uses a quantum decision theory model that explains irrational action choices in human decision making. The second approach uses a quantum game theory model that exploits the quantum mechanical phenomena "entanglement" to increase individual pay-off in multi-player games. The efficiency and scalability of the proposed coordination models are demonstrated through simulations of a large scale multi-agent system.
Notlar:
School code: 0587
Tüzel Kişi Ek Girişi:
Mevcut:*
Yer Numarası | Demirbaş Numarası | Shelf Location | Lokasyon / Statüsü / İade Tarihi |
---|---|---|---|
XX(687522.1) | 687522-1001 | 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.