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

Function Approximation-based Reinfor...

Li, Wei.

FindBook

Google Book

Amazon

博客來

Function Approximation-based Reinforcement Learning for Large-scale Problem Domains.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Function Approximation-based Reinforcement Learning for Large-scale Problem Domains./
作者:	Li, Wei.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2019,
面頁冊數:	146 p.
附註:	Source: Dissertations Abstracts International, Volume: 80-12, Section: B.
Contained By:	Dissertations Abstracts International80-12B.
標題:	Computer Engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13809755
ISBN:	9781392150559

Function Approximation-based Reinforcement Learning for Large-scale Problem Domains.
Li, Wei.

Function Approximation-based Reinforcement Learning for Large-scale Problem Domains. - Ann Arbor : ProQuest Dissertations & Theses, 2019 - 146 p.

Source: Dissertations Abstracts International, Volume: 80-12, Section: B.

Thesis (Ph.D.)--Northeastern University, 2019.

This item must not be sold to any third party vendors.

Reinforcement learning (RL) encounters the increasing challenge of maintaining good performance in emerging large-scale real-world problems. Function approximation is the key technique to solve the performance degradation issues when implementing RL algorithms in problems with continuous and/or large environments. In such problem domains, the number of state-action values necessary to be stored and the time to fully explore the task environment can be dramatically large, significantly impeding the RL agent's progress to solve hard problems with high performance. Function approximation techniques handle this challenge by representing the state-acton values with a limited number of parametric components while in the meanwhile obtaining generalization ability and shortening convergence time. However, when solving real-world problems with very complex environments, current function approximation algorithms cannot guarantee satisfactory performance.In this dissertation, we develop new function approximation techniques and apply them to two difficult real-world problems: the TCP congestion control and the video streaming bitrate adaptation. We show that applying reinforcement learning using an uncompressed table, or even a parameterized table with existing function approximation techniques to store learned state-action values, can give poor performance in these continuous and large-scale domains. To solve the performance degradation issues, we study the architecture of Sparse Distributed Memories (SDMs, also called Kanerva coding) and extend it by designing new function approximators with significantly improved performance in terms of effectiveness, efficiency and adaptability.We describe three novel online function approximators, each of which has its own strengths and suitable applications. We evaluate their performance on classic testbeds: the Mountain Car and the Hunter-Prey problems. We then show that they are able to solve the TCP congestion control and video streaming bitrate adaptation problems with significant performance improvements compared to state-of-the-art techniques.

ISBN: 9781392150559Subjects--Topical Terms:

1567821
Computer Engineering.

Function Approximation-based Reinforcement Learning for Large-scale Problem Domains.
LDR:03170nmm a2200313 4500 001 2207651
005 20190920102354.5
008 201008s2019 ||||||||||||||||| ||eng d
020 $a 9781392150559
035 $a (MiAaPQ)AAI13809755
035 $a (MiAaPQ)coe.neu:11147
035 $a AAI13809755
040 $a MiAaPQ $c MiAaPQ
100 1 $a Li, Wei. $3 884990
245 1 0 $a Function Approximation-based Reinforcement Learning for Large-scale Problem Domains.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2019
300 $a 146 p.
500 $a Source: Dissertations Abstracts International, Volume: 80-12, Section: B.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Meleis, Waleed.
502 $a Thesis (Ph.D.)--Northeastern University, 2019.
506 $a This item must not be sold to any third party vendors.
520 $a Reinforcement learning (RL) encounters the increasing challenge of maintaining good performance in emerging large-scale real-world problems. Function approximation is the key technique to solve the performance degradation issues when implementing RL algorithms in problems with continuous and/or large environments. In such problem domains, the number of state-action values necessary to be stored and the time to fully explore the task environment can be dramatically large, significantly impeding the RL agent's progress to solve hard problems with high performance. Function approximation techniques handle this challenge by representing the state-acton values with a limited number of parametric components while in the meanwhile obtaining generalization ability and shortening convergence time. However, when solving real-world problems with very complex environments, current function approximation algorithms cannot guarantee satisfactory performance.In this dissertation, we develop new function approximation techniques and apply them to two difficult real-world problems: the TCP congestion control and the video streaming bitrate adaptation. We show that applying reinforcement learning using an uncompressed table, or even a parameterized table with existing function approximation techniques to store learned state-action values, can give poor performance in these continuous and large-scale domains. To solve the performance degradation issues, we study the architecture of Sparse Distributed Memories (SDMs, also called Kanerva coding) and extend it by designing new function approximators with significantly improved performance in terms of effectiveness, efficiency and adaptability.We describe three novel online function approximators, each of which has its own strengths and suitable applications. We evaluate their performance on classic testbeds: the Mountain Car and the Hunter-Prey problems. We then show that they are able to solve the TCP congestion control and video streaming bitrate adaptation problems with significant performance improvements compared to state-of-the-art techniques.
590 $a School code: 0160.
650 4 $a Computer Engineering. $3 1567821
690 $a 0464
710 2 $a Northeastern University. $b Electrical and Computer Engineering. $3 1018491
773 0 $t Dissertations Abstracts International $g 80-12B.
790 $a 0160
791 $a Ph.D.
792 $a 2019
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13809755