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

Perception-based generalization in m...

Rutgers The State University of New Jersey - New Brunswick., Graduate School - New Brunswick.

FindBook

Google Book

Amazon

博客來

Perception-based generalization in model-based reinforcement learning.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Perception-based generalization in model-based reinforcement learning./
作者:	Leffler, Bethany R.
面頁冊數:	120 p.
附註:	Adviser: Michael L. Littman.
Contained By:	Dissertation Abstracts International70-03B.
標題:	Artificial Intelligence. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoeng/servlet/advanced?query=3350163
ISBN:	9781109072754

Perception-based generalization in model-based reinforcement learning.
Leffler, Bethany R.

Perception-based generalization in model-based reinforcement learning. - 120 p.

Adviser: Michael L. Littman.

Thesis (Ph.D.)--Rutgers The State University of New Jersey - New Brunswick, 2009.

In recent years, the advances in robotics have allowed for robots to venture into places too dangerous for humans. Unfortunately, the terrain in which these robots are being deployed may not be known by humans in advance, making it difficult to create motion programs robust enough to handle all scenarios that the robot may encounter. For this reason, research is being done to add learning capabilities to improve the robot's ability to adapt to its environment. Reinforcement learning is well suited for these robot domains because often the desired outcome is known, but the best way to achieve this outcome is unknown.

ISBN: 9781109072754Subjects--Topical Terms:

769149
Artificial Intelligence.

Perception-based generalization in model-based reinforcement learning.
LDR:03315nam 2200313 a 45 001 857000
005 20100709
008 100709s2009 ||||||||||||||||| ||eng d
020 $a 9781109072754
035 $a (UMI)AAI3350163
035 $a AAI3350163
040 $a UMI $c UMI
100 1 $a Leffler, Bethany R. $3 1023900
245 1 0 $a Perception-based generalization in model-based reinforcement learning.
300 $a 120 p.
500 $a Adviser: Michael L. Littman.
500 $a Source: Dissertation Abstracts International, Volume: 70-03, Section: B, page: 1757.
502 $a Thesis (Ph.D.)--Rutgers The State University of New Jersey - New Brunswick, 2009.
520 $a In recent years, the advances in robotics have allowed for robots to venture into places too dangerous for humans. Unfortunately, the terrain in which these robots are being deployed may not be known by humans in advance, making it difficult to create motion programs robust enough to handle all scenarios that the robot may encounter. For this reason, research is being done to add learning capabilities to improve the robot's ability to adapt to its environment. Reinforcement learning is well suited for these robot domains because often the desired outcome is known, but the best way to achieve this outcome is unknown.
520 $a In a real world domain, a reinforcement-learning agent has to learn a great deal from experience. Therefore, it must be sample-size efficient. To do so, it must balance the amount of exploration that is needed to properly model the environment with the need to use the information that it has already obtained to complete its original task. In robot domains, the exploration process is especially costly in both time and energy. Therefore, it is important to make the best possible use of the robot's limited opportunities for exploration without degrading the robot's performance.
520 $a This dissertation discusses a specialization of the standard Markov Decision Process (MDP) framework that allows for easier transfer of experience between similar states and introduces an algorithm that uses this new framework to perform more efficient exploration in robot-navigation problems. It then develops methods for an agent to determine how to accurately group similar states. One proposed technique clusters states by their observed outcomes. To make it possible to extrapolate observed outcomes to as-yet unvisited states, a second approach uses perceptual information such as the output of an image-processing system to group perceptually similar states with the hope that they will also be related in terms of outcomes. However, there are many different percepts from which a robot could obtain state groupings. To address this issue, a third algorithm is presented that determines how to group states when the agent has multiple, possibly conflicting, inputs from which to choose. Robot experiments of all algorithms proposed are included to demonstrate the improvements that can be obtained by using the approaches presented.
590 $a School code: 0190.
650 4 $a Artificial Intelligence. $3 769149
650 4 $a Computer Science. $3 626642
650 4 $a Engineering, Robotics. $3 1018454
690 $a 0771
690 $a 0800
690 $a 0984
710 2 $a Rutgers The State University of New Jersey - New Brunswick. $b Graduate School - New Brunswick. $3 1019196
773 0 $t Dissertation Abstracts International $g 70-03B.
790 $a 0190
790 1 0 $a Littman, Michael L., $e advisor
791 $a Ph.D.
792 $a 2009
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoeng/servlet/advanced?query=3350163