DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Joungho | - |
dc.contributor.advisor | 김정호 | - |
dc.contributor.author | Lho, Daehwan | - |
dc.date.accessioned | 2023-06-23T19:33:35Z | - |
dc.date.available | 2023-06-23T19:33:35Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1030555&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/309079 | - |
dc.description | 학위논문(박사) - 한국과학기술원 : 전기및전자공학부, 2023.2,[iii, 37 p. :] | - |
dc.description.abstract | In this article, we propose for the first time a constructive deep deterministic policy-based reinforcement learning method for optimizing DDR5 memory signaling architectures. The proposed method is a design optimization methodology for maximizing the eye diagram, which is a performance indicator of the channel for many factors such as desired components and termination and decision feedback equalizer, in the entire channel from the processor to the memory in order to improve the limitations of the DDR5 channel. Deterministic policy is used to optimize successive factors, and deterministic policy-based reinforcement learning based on constructive neural networks is used to reflect the association of many factors being optimized. The proposed method can be reused because the result can be obtained immediately even if the values of a given environment are changed. To verify the optimality and optimization time of the proposed methodology, we compared the lattice search method based on the Latin hyperbolic sampling method, the random search method, and the conventional optimization methods such as the Bayesian optimization method, and probabilistic policies such as the advanced actor critical and proximity policy optimization. We compared it with the reinforcement learning method based on it. As a result, the proposed method proved to be the best method in terms of optimization performance, optimization time, and reusability. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Memory architecture▼aSignal integrity▼aReinforcement learning▼aDeterministic policy▼aConstructive neural network | - |
dc.subject | 메모리 아키텍쳐▼a신호 무결성▼a강화 학습▼a결정론적 정책▼a건설적인 신경망 | - |
dc.title | Constructive deep deterministic policy-based reinforcement learning method for optimization of DDR5 memory signaling architecture | - |
dc.title.alternative | DDR5 메모리 시그널링 아키텍처 최적화를 위한 건설적 심층 결정론적 정책 기반 강화 학습 방법 | - |
dc.type | Thesis(Ph.D) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 노대환 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.