東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Application of temporal difference l...

Lockhart, Christopher.

FindBook

Google Book

Amazon

博客來

Application of temporal difference learning to the game of Snake.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Application of temporal difference learning to the game of Snake./
作者:	Lockhart, Christopher.
面頁冊數:	96 p.
附註:	Source: Masters Abstracts International, Volume: 48-06, page: 3717.
Contained By:	Masters Abstracts International48-06.
標題:	Engineering, Computer. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1485160
ISBN:	9781124102832

Application of temporal difference learning to the game of Snake.
Lockhart, Christopher.

Application of temporal difference learning to the game of Snake. - 96 p.

Source: Masters Abstracts International, Volume: 48-06, page: 3717.

Thesis (M.Eng.)--University of Louisville, 2010.

The game of Snake has been selected to provide a unique application of the TD(lambda) algorithm as proposed by Sutton. A reinforcement learning technique for producing computer controlled players is documented. Using value function approximation with multilayer artificial neural networks and the actor-critic architecture, computer players capable of playing the game of Snake can be created. The adaptation to the standard neural network backpropagation procedure will be documented. Not only does the proposed technique provide reasonable player performance, its application is unique; this approach to Snake has never been documented. By performing sets of trials, the performance of the players are evaluated and compared against an existing machine learning technique. Learning curves provide visualization for the results. Though the snake players are shown to be capable of achieving lower scores than with the existing method, the technique is able to produce agents that accumulate scores, much more efficiently.

ISBN: 9781124102832Subjects--Topical Terms:

1669061
Engineering, Computer.

Application of temporal difference learning to the game of Snake.
LDR:01873nam 2200277 4500 001 1399927
005 20110930095912.5
008 130515s2010 ||||||||||||||||| ||eng d
020 $a 9781124102832
035 $a (UMI)AAI1485160
035 $a AAI1485160
040 $a UMI $c UMI
100 1 $a Lockhart, Christopher. $3 1678936
245 1 0 $a Application of temporal difference learning to the game of Snake.
300 $a 96 p.
500 $a Source: Masters Abstracts International, Volume: 48-06, page: 3717.
500 $a Adviser: Ahmed Desoky.
502 $a Thesis (M.Eng.)--University of Louisville, 2010.
520 $a The game of Snake has been selected to provide a unique application of the TD(lambda) algorithm as proposed by Sutton. A reinforcement learning technique for producing computer controlled players is documented. Using value function approximation with multilayer artificial neural networks and the actor-critic architecture, computer players capable of playing the game of Snake can be created. The adaptation to the standard neural network backpropagation procedure will be documented. Not only does the proposed technique provide reasonable player performance, its application is unique; this approach to Snake has never been documented. By performing sets of trials, the performance of the players are evaluated and compared against an existing machine learning technique. Learning curves provide visualization for the results. Though the snake players are shown to be capable of achieving lower scores than with the existing method, the technique is able to produce agents that accumulate scores, much more efficiently.
590 $a School code: 0110.
650 4 $a Engineering, Computer. $3 1669061
650 4 $a Computer Science. $3 626642
690 $a 0464
690 $a 0984
710 2 $a University of Louisville. $3 1017614
773 0 $t Masters Abstracts International $g 48-06.
790 1 0 $a Desoky, Ahmed, $e advisor
790 $a 0110
791 $a M.Eng.
792 $a 2010
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1485160