東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Autonomous qualitative learning of d...

Mugan, Jonathan William.

Linked to FindBook

Google Book

Amazon

博客來

Autonomous qualitative learning of distinctions and actions in a developing agent.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Autonomous qualitative learning of distinctions and actions in a developing agent./
Author:	Mugan, Jonathan William.
Description:	189 p.
Notes:	Source: Dissertation Abstracts International, Volume: 71-11, Section: B, page: 6889.
Contained By:	Dissertation Abstracts International71-11B.
Subject:	Engineering, Robotics. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3428996
ISBN:	9781124281346

Autonomous qualitative learning of distinctions and actions in a developing agent.
Mugan, Jonathan William.

Autonomous qualitative learning of distinctions and actions in a developing agent. - 189 p.

Source: Dissertation Abstracts International, Volume: 71-11, Section: B, page: 6889.

Thesis (Ph.D.)--The University of Texas at Austin, 2010.

How can an agent bootstrap up from a pixel-level representation to autonomously learn high-level states and actions using only domain general knowledge? This thesis attacks a piece of this problem and assumes that an agent has a set of continuous variables describing the environment and a set of continuous motor primitives, and poses a solution for the problem of how an agent can learn a set of useful states and effective higher-level actions through autonomous experience with the environment. There exist methods for learning models of the environment, and there also exist methods for planning. However, for autonomous learning, these methods have been used almost exclusively in discrete environments.

ISBN: 9781124281346Subjects--Topical Terms:

1018454
Engineering, Robotics.

Autonomous qualitative learning of distinctions and actions in a developing agent.
LDR:02821nam 2200301 4500 001 1405157
005 20111206130422.5
008 130515s2010 ||||||||||||||||| ||eng d
020 $a 9781124281346
035 $a (UMI)AAI3428996
035 $a AAI3428996
040 $a UMI $c UMI
100 1 $a Mugan, Jonathan William. $3 1684515
245 1 0 $a Autonomous qualitative learning of distinctions and actions in a developing agent.
300 $a 189 p.
500 $a Source: Dissertation Abstracts International, Volume: 71-11, Section: B, page: 6889.
500 $a Adviser: Benjamin J. Kuipers.
502 $a Thesis (Ph.D.)--The University of Texas at Austin, 2010.
520 $a How can an agent bootstrap up from a pixel-level representation to autonomously learn high-level states and actions using only domain general knowledge? This thesis attacks a piece of this problem and assumes that an agent has a set of continuous variables describing the environment and a set of continuous motor primitives, and poses a solution for the problem of how an agent can learn a set of useful states and effective higher-level actions through autonomous experience with the environment. There exist methods for learning models of the environment, and there also exist methods for planning. However, for autonomous learning, these methods have been used almost exclusively in discrete environments.
520 $a This thesis proposes attacking the problem of learning high-level states and actions in continuous environments by using a qualitative representation to bridge the gap between continuous and discrete variable representations. In this approach, the agent begins with a broad discretization and initially can only tell if the value of each variable is increasing, decreasing, or remaining steady. The agent then simultaneously learns a qualitative representation (discretization) and a set of predictive models of the environment. The agent then converts these models into plans to form actions. The agent then uses those learned actions to explore the environment.
520 $a The method is evaluated using a simulated robot with realistic physics. The robot is sitting at a table that contains one or two blocks, as well as other distractor objects that are out of reach. The agent autonomously explores the environment without being given a task. After learning, the agent is given various tasks to determine if it learned the necessary states and actions to complete them. The results show that the agent was able to use this method to autonomously learn to perform the tasks.
590 $a School code: 0227.
650 4 $a Engineering, Robotics. $3 1018454
650 4 $a Computer Science. $3 626642
690 $a 0771
690 $a 0984
710 2 $a The University of Texas at Austin. $3 718984
773 0 $t Dissertation Abstracts International $g 71-11B.
790 1 0 $a Kuipers, Benjamin J., $e advisor
790 $a 0227
791 $a Ph.D.
792 $a 2010
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3428996