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

First order Markov decision processes.

Wang, Chenggang.

Linked to FindBook

Google Book

Amazon

博客來

First order Markov decision processes.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	First order Markov decision processes./
Author:	Wang, Chenggang.
Description:	161 p.
Notes:	Adviser: Roni Khardon.
Contained By:	Dissertation Abstracts International68-03B.
Subject:	Computer Science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3258348

First order Markov decision processes.
Wang, Chenggang.

First order Markov decision processes. - 161 p.

Adviser: Roni Khardon.

Thesis (Ph.D.)--Tufts University, 2007.

Relational Markov Decision Processes (RMDP) are a useful abstraction for complex reinforcement learning problems and stochastic planning problems since one can develop abstract solutions for them that are independent of domain size or instantiation. This thesis develops compact representations for RMDPs and exact solution methods for RMDPs using such representations. One of the core contributions of the thesis is development of the First Order Decision Diagram (FODD), a representation that captures functions over relational structures, together with a set of operators to manipulate FODDs. FODDs offer a potentially compact representation for complex functions over relational structures and can therefore serve as underlying engine for efficient algorithms with relational structures. The second core contribution is developing exact solution methods for RMDPs based on FODD representations. In particular FODDs are used to represent value functions, transition probabilities, and domain dynamics of RMDPs. Special operations are developed to implement exact value iteration and a novel variant of policy iteration and the algorithms are shown to calculate optimal solutions for RMDPs. Finally we show how the algorithms for RMDPs using FODDs can be extended to handle relational Partially Observable MDPs.Subjects--Topical Terms:

626642
Computer Science.

First order Markov decision processes.
LDR:02092nam 2200253 a 45 001 941903
005 20110519
008 110519s2007 ||||||||||||||||| ||eng d
035 $a (UMI)AAI3258348
035 $a AAI3258348
040 $a UMI $c UMI
100 1 $a Wang, Chenggang. $3 1266001
245 1 0 $a First order Markov decision processes.
300 $a 161 p.
500 $a Adviser: Roni Khardon.
500 $a Source: Dissertation Abstracts International, Volume: 68-03, Section: B, page: 1743.
502 $a Thesis (Ph.D.)--Tufts University, 2007.
520 $a Relational Markov Decision Processes (RMDP) are a useful abstraction for complex reinforcement learning problems and stochastic planning problems since one can develop abstract solutions for them that are independent of domain size or instantiation. This thesis develops compact representations for RMDPs and exact solution methods for RMDPs using such representations. One of the core contributions of the thesis is development of the First Order Decision Diagram (FODD), a representation that captures functions over relational structures, together with a set of operators to manipulate FODDs. FODDs offer a potentially compact representation for complex functions over relational structures and can therefore serve as underlying engine for efficient algorithms with relational structures. The second core contribution is developing exact solution methods for RMDPs based on FODD representations. In particular FODDs are used to represent value functions, transition probabilities, and domain dynamics of RMDPs. Special operations are developed to implement exact value iteration and a novel variant of policy iteration and the algorithms are shown to calculate optimal solutions for RMDPs. Finally we show how the algorithms for RMDPs using FODDs can be extended to handle relational Partially Observable MDPs.
590 $a School code: 0234.
650 4 $a Computer Science. $3 626642
690 $a 0984
710 2 $a Tufts University. $3 1017847
773 0 $t Dissertation Abstracts International $g 68-03B.
790 $a 0234
790 1 0 $a Khardon, Roni, $e advisor
791 $a Ph.D.
792 $a 2007
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3258348