以自我組織特徵映射圖為基礎之模糊系統實作連續性Q-learning; A SOM-based Fuzzy Systems Q-learning in Continuous State and Action Space

NCU Institutional Repository > 資訊電機學院 > 資訊工程研究所 > 博碩士論文 > Item 987654321/9287

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/9287

题名:	以自我組織特徵映射圖為基礎之模糊系統實作連續性Q-learning;A SOM-based Fuzzy Systems Q-learning in Continuous State and Action Space
作者:	陳律宇;Lu-Yu Chen
贡献者:	資訊工程研究所
关键词:	任務分解;連續性Q-learning;增強式學習;自我組織特徵映射圖;continuous Q-learning;task decomposition;self-organizing feature map;reinforcement learning
日期:	2006-07-06
上传时间:	2009-09-22 11:44:42 (UTC+8)
出版者:	國立中央大學圖書館
摘要:	所謂的增強式學習法（Reinforcement Learning），就是訓練對象與環境互動的過程中，不藉助監督者提供完整的指令下，可以自行發掘在各種狀態下該採取什麼行動才能獲得最大報酬。而Q-learning 是一種常見的增強式學習法，藉由建立每一個狀態對應每一個動作之Q值的查詢表（look-up table），Q-learning 可以順利的處理存在少量離散狀態與動作空間的問題上。但當處理的問題擁有大量的狀態與動作時，所要建立的查詢表便會十分的巨大，所以此種對於每一個狀態－動作建立查詢表的方法便顯得不可行。本論文提出一個以自我組織特徵映射網路（Self-Organization Feature Map network, SOM network）為基礎的模糊系統來實作Q-learning，並以此方法來設計控制系統。為了加速訓練的過程，本論文結合任務分解（task decomposition）與自動任務分解的機制來處理複雜的任務。藉由機器人的模擬實驗，可以看出此方法的有效性。 In reinforcement learning, there is no supervisor to critically judge the chosen action at each step. The learning is through a trial-and-error procedure interacting with a dynamic environment. Q-learning is one popular approach to reinforcement learning. It is widely applied to problems with discrete states and actions and usually implemented by a look-up table where each item corresponds to a combination of a state and an action. However, the look-up table plementation of Q-learning fails in problems with continuous state and action space because an exhaustive enumeration of all state-action pairs is impossible. In this thesis, an implementation of Q-learning for solving problems with continuous state and action space using SOM-based fuzzy systems is proposed. Simulations of training a robot to complete two different tasks are used to demonstrate the effectiveness of the proposed approach. Reinforcement learning usually is a slow process. In order to accelerate the learning procedure, a hybrid approach which integrates the advantages of the ideas of hierarchical learning and the progressive learning to decompose a complex task into simple elementary tasks is proposed.
显示于类别:	[資訊工程研究所] 博碩士論文

文件中的档案:

档案	大小	格式	浏览次数

在NCUIR中所有的数据项都受到原著作权保护.

社群 sharing

数据加载中.....