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

Linked to FindBook

Google Book

Amazon

博客來

Efficient Communication Via Reinforcement Learning.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Efficient Communication Via Reinforcement Learning./
Author:	Carlsson, Emil.
Description:	1 online resource (75 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 83-11, Section: B.
Contained By:	Dissertations Abstracts International83-11B.
Subject:	Language. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29071974click for full text (PQDT)
ISBN:	9798426879652

Efficient Communication Via Reinforcement Learning.
Carlsson, Emil.

Efficient Communication Via Reinforcement Learning. - 1 online resource (75 pages)

Source: Dissertations Abstracts International, Volume: 83-11, Section: B.

Thesis (Ph.D.)--Chalmers Tekniska Hogskola (Sweden), 2022.

Includes bibliographical references

Why do languages partition mental concepts into words the way the do? Recent works have taken a information-theoretic view on human language and suggested that it is shaped by the need for efficient communication (Regier et al., 2015; Gibson et al., 2017; Zaslavsky et al., 2018). This means that human language is shaped by a simultaneous pressure for being informative, while also being simple in order to minimize the cognitive load.In this thesis we combine the information-theoretic perspective on language with recent advances in deep multi-agent reinforcement learning. We explore how efficient communication emerges between two artificial agents in a signaling game as a by-product of them maximizing a shared reward signal. This is tested in the domain of colors and numeral systems, two domains in which human languages tends to support efficient communication (Zaslavsky et al., 2018; Xu et al., 2020). We find that the communication developed by the artificial agents in these domains shares characteristics with human languages when it comes to efficiency and structure of semantic partitions. even though the agents lack the full perceptual and linguistic architecture of humans.Our results offer a computational learning perspective that may complement the information-theoretic view on the structure of human languages. The results also suggests that reinforcement learning is a powerful and flexible framework that can be used to test and generate hypotheses in silico.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798426879652Subjects--Topical Terms:

643551
Language.
Index Terms--Genre/Form:

542853
Electronic books.

Efficient Communication Via Reinforcement Learning.
LDR:02832nmm a2200409K 4500 001 2354412
005 20230414084750.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798426879652
035 $a (MiAaPQ)AAI29071974
035 $a (MiAaPQ)Chalmers_SE528032
035 $a AAI29071974
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Carlsson, Emil. $3 3694765
245 1 0 $a Efficient Communication Via Reinforcement Learning.
264 0 $c 2022
300 $a 1 online resource (75 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 83-11, Section: B.
500 $a Advisor: Dubhashi, Devdatt.
502 $a Thesis (Ph.D.)--Chalmers Tekniska Hogskola (Sweden), 2022.
504 $a Includes bibliographical references
520 $a Why do languages partition mental concepts into words the way the do? Recent works have taken a information-theoretic view on human language and suggested that it is shaped by the need for efficient communication (Regier et al., 2015; Gibson et al., 2017; Zaslavsky et al., 2018). This means that human language is shaped by a simultaneous pressure for being informative, while also being simple in order to minimize the cognitive load.In this thesis we combine the information-theoretic perspective on language with recent advances in deep multi-agent reinforcement learning. We explore how efficient communication emerges between two artificial agents in a signaling game as a by-product of them maximizing a shared reward signal. This is tested in the domain of colors and numeral systems, two domains in which human languages tends to support efficient communication (Zaslavsky et al., 2018; Xu et al., 2020). We find that the communication developed by the artificial agents in these domains shares characteristics with human languages when it comes to efficiency and structure of semantic partitions. even though the agents lack the full perceptual and linguistic architecture of humans.Our results offer a computational learning perspective that may complement the information-theoretic view on the structure of human languages. The results also suggests that reinforcement learning is a powerful and flexible framework that can be used to test and generate hypotheses in silico.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Language. $3 643551
650 4 $a Communication channels. $3 3560268
650 4 $a Deep learning. $3 3554982
650 4 $a Artificial intelligence. $3 516317
650 4 $a Neural networks. $3 677449
650 4 $a Neurosciences. $3 588700
650 4 $a Games. $3 525308
650 4 $a Cognition & reasoning. $3 3556293
650 4 $a Markov analysis. $3 3562906
650 4 $a Semantics. $3 520060
650 4 $a Cognitive psychology. $3 523881
650 4 $a Communication. $3 524709
650 4 $a Linguistics. $3 524476
650 4 $a Operations research. $3 547123
650 4 $a Psychology. $3 519075
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0679
690 $a 0800
690 $a 0317
690 $a 0633
690 $a 0459
690 $a 0290
690 $a 0796
690 $a 0621
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a Chalmers Tekniska Hogskola (Sweden). $3 1913472
773 0 $t Dissertations Abstracts International $g 83-11B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29071974 $z click for full text (PQDT)