語系:
繁體中文
English
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
Neurocomputational mechanisms of rei...
~
Cohen, Michael Steven.
FindBook
Google Book
Amazon
博客來
Neurocomputational mechanisms of reinforcement learning.
紀錄類型:
書目-電子資源 : Monograph/item
正題名/作者:
Neurocomputational mechanisms of reinforcement learning./
作者:
Cohen, Michael Steven.
出版者:
Ann Arbor : ProQuest Dissertations & Theses, : 2007,
面頁冊數:
108 p.
附註:
Source: Dissertations Abstracts International, Volume: 69-07, Section: B.
Contained By:
Dissertations Abstracts International69-07B.
標題:
Cognitive therapy. -
電子資源:
http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3282958
ISBN:
9780549253808
Neurocomputational mechanisms of reinforcement learning.
Cohen, Michael Steven.
Neurocomputational mechanisms of reinforcement learning.
- Ann Arbor : ProQuest Dissertations & Theses, 2007 - 108 p.
Source: Dissertations Abstracts International, Volume: 69-07, Section: B.
Thesis (Ph.D.)--University of California, Davis, 2007.
Our world is filled with uncertainty and limited resources. Nearly every decision we face is clouded in uncertainty-uncertainty about the consequences of our decisions, uncertainty about whether others will obtain resources before we do, uncertainty about how different individuals will respond in similar contexts. Fortunately, we are often faced with the same or similar decision problems repeatedly, providing the opportunity to learn from our previous decisions and outcomes, and dynamically adapt decision-making strategies in the service of maximizing good outcomes and minimizing bad outcomes. Theories and computational models of reinforcement learning provide a biologically and mathematically grounded framework within which to characterize, predict, and understand the behavioral, cognitive, and neural bases of reward-guided decision-making. Neuroscience research is making strides in mapping out the neurocomputational mechanisms of reinforcement learning, at approaches spanning synaptic, neurochemical, systems, and large neural network. Much of this nascent research has focused on elucidating the neural systems and computations that underlie instantaneous reinforcement processing-that is, how we are able to identify whether environmental stimuli or consequences of our actions are relatively good or bad. In contrast, however, little research has focused on the mechanisms by which reinforcements might be used to guide future decision-making. I have attempted to help bridge this gap by designing research studies and analysis approaches to better characterize how humans use reward information to guide and optimize their decision-making. The research detailed here represents my first attempts to characterize the neurocomputational mechanisms involved in reinforcement learning, and therefore my efforts to help move the field forward, from studying the mechanisms of reinforcement processing to the mechanisms of reinforcement learning.
ISBN: 9780549253808Subjects--Topical Terms:
524357
Cognitive therapy.
Neurocomputational mechanisms of reinforcement learning.
LDR
:02845nmm a2200277 4500
001
2206864
005
20190906083303.5
008
201008s2007 ||||||||||||||||| ||eng d
020
$a
9780549253808
035
$a
(MiAaPQ)AAI3282958
035
$a
AAI3282958
040
$a
MiAaPQ
$c
MiAaPQ
100
1
$a
Cohen, Michael Steven.
$3
3433783
245
1 0
$a
Neurocomputational mechanisms of reinforcement learning.
260
1
$a
Ann Arbor :
$b
ProQuest Dissertations & Theses,
$c
2007
300
$a
108 p.
500
$a
Source: Dissertations Abstracts International, Volume: 69-07, Section: B.
500
$a
Publisher info.: Dissertation/Thesis.
502
$a
Thesis (Ph.D.)--University of California, Davis, 2007.
520
$a
Our world is filled with uncertainty and limited resources. Nearly every decision we face is clouded in uncertainty-uncertainty about the consequences of our decisions, uncertainty about whether others will obtain resources before we do, uncertainty about how different individuals will respond in similar contexts. Fortunately, we are often faced with the same or similar decision problems repeatedly, providing the opportunity to learn from our previous decisions and outcomes, and dynamically adapt decision-making strategies in the service of maximizing good outcomes and minimizing bad outcomes. Theories and computational models of reinforcement learning provide a biologically and mathematically grounded framework within which to characterize, predict, and understand the behavioral, cognitive, and neural bases of reward-guided decision-making. Neuroscience research is making strides in mapping out the neurocomputational mechanisms of reinforcement learning, at approaches spanning synaptic, neurochemical, systems, and large neural network. Much of this nascent research has focused on elucidating the neural systems and computations that underlie instantaneous reinforcement processing-that is, how we are able to identify whether environmental stimuli or consequences of our actions are relatively good or bad. In contrast, however, little research has focused on the mechanisms by which reinforcements might be used to guide future decision-making. I have attempted to help bridge this gap by designing research studies and analysis approaches to better characterize how humans use reward information to guide and optimize their decision-making. The research detailed here represents my first attempts to characterize the neurocomputational mechanisms involved in reinforcement learning, and therefore my efforts to help move the field forward, from studying the mechanisms of reinforcement processing to the mechanisms of reinforcement learning.
590
$a
School code: 0029.
650
4
$a
Cognitive therapy.
$3
524357
650
4
$a
Neurology.
$3
588698
650
4
$a
Computers.
$3
544777
650
4
$a
Learning.
$3
516521
690
$a
0633
710
2
$a
University of California, Davis.
$3
1018682
773
0
$t
Dissertations Abstracts International
$g
69-07B.
790
$a
0029
791
$a
Ph.D.
792
$a
2007
793
$a
English
856
4 0
$u
http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3282958
筆 0 讀者評論
館藏地:
全部
電子資源
出版年:
卷號:
館藏
1 筆 • 頁數 1 •
1
條碼號
典藏地名稱
館藏流通類別
資料類型
索書號
使用類型
借閱狀態
預約狀態
備註欄
附件
W9383413
電子資源
11.線上閱覽_V
電子書
EB
一般使用(Normal)
在架
0
1 筆 • 頁數 1 •
1
多媒體
評論
新增評論
分享你的心得
Export
取書館
處理中
...
變更密碼
登入