An action-oriented perspective of learning in classifier systems
Classifier systems constitute a general model of low-level rule-based systems that are capable of environmental interaction and learning. A central characteristic and drawback of the traditional approaches to learning in such systems is that they exclusively work on the rule level, without taking in...
Saved in:
| Published in | Journal of experimental & theoretical artificial intelligence Vol. 8; no. 1; pp. 43 - 62 |
|---|---|
| Main Author | |
| Format | Journal Article |
| Language | English |
| Published |
Taylor & Francis Group
01.01.1996
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Classifier systems constitute a general model of low-level rule-based systems that are capable of environmental interaction and learning. A central characteristic and drawback of the traditional approaches to learning in such systems is that they exclusively work on the rule level, without taking into consideration that the individual rules possess a very complex activity behaviour. This article investigates an alternative, action-oriented perspective of learning in classifier systems which does not suffer from this drawback. According to this perspective learning is realized on the finer action level instead of the coarser rule level. Comparative theoretical and experimental results are presented that show the advantages of the action-oriented over the traditional perspective. |
|---|---|
| AbstractList | Classifier systems constitute a general model of low-level rule-based systems that are capable of environmental interaction and learning. A central characteristic and drawback of the traditional approaches to learning in such systems is that they exclusively work on the rule level, without taking into consideration that the individual rules possess a very complex activity behaviour. This article investigates an alternative, action-oriented perspective of learning in classifier systems which does not suffer from this drawback. According to this perspective learning is realized on the finer action level instead of the coarser rule level. Comparative theoretical and experimental results are presented that show the advantages of the action-oriented over the traditional perspective. |
| Author | WEIss, GERHARD |
| Author_xml | – sequence: 1 givenname: GERHARD surname: WEIss fullname: WEIss, GERHARD |
| BookMark | eNp1kMFKAzEYhINUsK0-gLe8wGr-zSabgAdL0SoUvCh4W9Lkj0S2SUkWZd_eLfUmngZm5pvDLMgspoiEXAO7AabYLdOiVsC1FIw1teDqjMyBy7rirNUzMj_m1VR4vyCLUj4ZYyAA5uR-FamxQ0ixSjlgHNDRA-ZywMn8Qpo87dHkGOIHDZHa3pQSfMBMy1gG3JdLcu5NX_DqV5fk7fHhdf1UbV82z-vVtrK1lkPVtN6aFpzWXCnnjLZaatEoMHUDTvgd4y1C45xtOHBea9wJLVuplZw4gXxJ4LRrcyolo-8OOexNHjtg3fGC7s8FE3N3YkL0Ke_Nd8q96wYz9in7bKINpeP_4z-7dmLw |
| CitedBy_id | crossref_primary_10_1155_2009_736398 |
| Cites_doi | 10.1016/0004-3702(94)90047-7 10.1016/0004-3702(89)90050-7 10.1016/B978-0-12-737550-2.50020-8 10.1109/AIHAS.1990.93934 10.1109/21.214773 10.1007/978-1-4757-1895-9_18 |
| ContentType | Journal Article |
| Copyright | Copyright Taylor & Francis Group, LLC 1996 |
| Copyright_xml | – notice: Copyright Taylor & Francis Group, LLC 1996 |
| DBID | AAYXX CITATION |
| DOI | 10.1080/09528139650042538 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1362-3079 |
| EndPage | 62 |
| ExternalDocumentID | 10_1080_09528139650042538 10132786 |
| Genre | Original Articles |
| GroupedDBID | .7F 07I 0BK 0R~ 1TA 29K 2DF 3YN 4.4 4B5 5GY 5VS 8VB 9M8 AAENE AAJMT AALDU AAMIU AAPUL AAQRR ABCCY ABFIM ABHAV ABIVO ABJNI ABLIJ ABMYL ABQHQ ABTAI ABXUL ABXYU ACGEJ ACGFS ACGOD ACTIO ADCVX ADGTB ADXEU ADXPE AEGXH AEHZU AEMOZ AENEX AEPSL AEYOC AEZBV AFION AFKVX AFWLO AGBLW AHDZW AIRXU AJWEG AKBVH AKHJE ALMA_UNASSIGNED_HOLDINGS ALQZU ALXIB AQRUH AVBZW AWYRJ BGSSV BLEHA C0- C5H CAG CCCUG COF CS3 D-I DEXXA DGEBU EAP EBR EBS EBU EJD ESX F5P FETWF GTTXZ HZ~ H~P IFELN IPNFZ J.P KYCEM L8C M4Z MVM NA5 NUSFT NX~ O9- P2P PQQKQ QWB RIG RNANH ROSJB RTWRZ S-T SNACF TAJZE TAP TEN TFL TFT TFW TNC TTHFI UB6 UT5 ZGOLN ZL0 .4S .DC .QJ 30N AAYXX ABDBF ABPAQ ABPEM ACTTO ADUMR AEGYZ AEISY AEOZL AGDLA AGMYJ AGVKY AGWUF AIJEM AKMBP AKOOK AKVCP ALRRR ARCSS BWMZZ CITATION CYRSC DAOYK DKSSO ECS EDO EMK EPL EST E~A E~B H13 HF~ I-F K1G LJTGL MK~ OPCYK TBQAZ TDBHL TH9 TUROJ TUS TWF UU3 ~S~ |
| ID | FETCH-LOGICAL-c296t-47fca71d99388dda9c9695481a241d5fb037e14ddc4313329eb59676986ca75e3 |
| ISSN | 0952-813X |
| IngestDate | Thu Sep 12 19:47:21 EDT 2024 Tue Mar 19 12:56:51 EDT 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c296t-47fca71d99388dda9c9695481a241d5fb037e14ddc4313329eb59676986ca75e3 |
| PageCount | 20 |
| ParticipantIDs | crossref_primary_10_1080_09528139650042538 informaworld_taylorfrancis_310_1080_09528139650042538 |
| PublicationCentury | 1900 |
| PublicationDate | 1/1/1996 1996-01-00 |
| PublicationDateYYYYMMDD | 1996-01-01 |
| PublicationDate_xml | – month: 01 year: 1996 text: 1/1/1996 day: 01 |
| PublicationDecade | 1990 |
| PublicationTitle | Journal of experimental & theoretical artificial intelligence |
| PublicationYear | 1996 |
| Publisher | Taylor & Francis Group |
| Publisher_xml | – name: Taylor & Francis Group |
| References | CIT0030 Booker L. B. (CIT0001) 1982 CIT0010 Hutter M. (CIT0018) 1991 CIT0032 Wilson S. W. (CIT0031) 1987 Riolo R. L. (CIT0020) 1988 Goldberg D. E. (CIT0008) 1983 Dorigo M. (CIT0005) 1991 Huang D. (CIT0016) 1989 CIT0013 Booker L. B. (CIT0002) 1988; 3 CIT0017 Robertson G. G. (CIT0023) 1988; 3 CIT0019 CIT0021 Holland J. H. (CIT0014) 1986; 1 CIT0022 Weiβ G. (CIT0025) 1991 Grefenstette J. J. (CIT0011) 1988; 3 Goldberg D. E. (CIT0009) 1989 CIT0003 Holland J. H. (CIT0015) 1978 CIT0024 CIT0027 CIT0004 CIT0026 CIT0007 Holland J. H. (CIT0012) 1975 CIT0029 CIT0006 CIT0028 |
| References_xml | – volume: 3 start-page: 225 year: 1988 ident: CIT0011 publication-title: Machine Learning contributor: fullname: Grefenstette J. J. – ident: CIT0017 – volume-title: CFS-C: A package of domain independent subroutin es for implementing classifier systems in arbitrary, user-defined environments year: 1988 ident: CIT0020 contributor: fullname: Riolo R. L. – ident: CIT0013 – ident: CIT0021 – ident: CIT0007 doi: 10.1016/0004-3702(94)90047-7 – ident: CIT0004 doi: 10.1016/0004-3702(89)90050-7 – volume: 3 start-page: 139 year: 1988 ident: CIT0023 publication-title: Machine Learning contributor: fullname: Robertson G. G. – volume-title: Genetic Algorithms in Search, Optimization, and Machine Learning year: 1989 ident: CIT0009 contributor: fullname: Goldberg D. E. – ident: CIT0027 – volume-title: New perspectives about default hierarchies formation in learning classifier systems year: 1991 ident: CIT0005 contributor: fullname: Dorigo M. – ident: CIT0029 – volume-title: Credit-apportionment in Rule-based Systems: Problem Analysis and Algorithm Synthesis year: 1989 ident: CIT0016 contributor: fullname: Huang D. – volume-title: Intelligent Behavior as an Adaptation to the Task Environment year: 1982 ident: CIT0001 contributor: fullname: Booker L. B. – start-page: 313 volume-title: Pattern-directed Inference Systems year: 1978 ident: CIT0015 doi: 10.1016/B978-0-12-737550-2.50020-8 contributor: fullname: Holland J. H. – start-page: 104 volume-title: Genetic Algorithms and Simulated Annealing year: 1987 ident: CIT0031 contributor: fullname: Wilson S. W. – ident: CIT0010 – ident: CIT0024 doi: 10.1109/AIHAS.1990.93934 – volume-title: Adaptation in Natural and Artificial Systems year: 1975 ident: CIT0012 contributor: fullname: Holland J. H. – volume: 1 start-page: 593 volume-title: Machine Learning: An Artificial Intelligence Approach year: 1986 ident: CIT0014 contributor: fullname: Holland J. H. – ident: CIT0003 – ident: CIT0026 – volume-title: The action-oriented bucket brigade year: 1991 ident: CIT0025 contributor: fullname: Weiβ G. – ident: CIT0028 – ident: CIT0006 doi: 10.1109/21.214773 – volume: 3 start-page: 161 year: 1988 ident: CIT0002 publication-title: Machine Learning contributor: fullname: Booker L. B. – ident: CIT0030 doi: 10.1007/978-1-4757-1895-9_18 – ident: CIT0032 – ident: CIT0022 – ident: CIT0019 – volume-title: Computer-aided Gas Pipeline Operation using Genetic Algorithms and Rule Learning year: 1983 ident: CIT0008 contributor: fullname: Goldberg D. E. – volume-title: Implementierung eines Klassifizierungssystems year: 1991 ident: CIT0018 contributor: fullname: Hutter M. |
| SSID | ssj0001511 |
| Score | 1.4455235 |
| Snippet | Classifier systems constitute a general model of low-level rule-based systems that are capable of environmental interaction and learning. A central... |
| SourceID | crossref informaworld |
| SourceType | Aggregation Database Publisher |
| StartPage | 43 |
| SubjectTerms | Classifier Systems Bucket Brigade Profit Sharing Plan Action-oriented Learning |
| Title | An action-oriented perspective of learning in classifier systems |
| URI | https://www.tandfonline.com/doi/abs/10.1080/09528139650042538 |
| Volume | 8 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3NT4MwFG90u3jx2zi_0oMnDWZQYPQm0Rn04MFscfFCgLYJiWGL4sW_3ldaPucS54UQAi30vfz6a3nv9xC6dK0hZ27kGS71hGG7ETdikRBDcJsQZ8jkqkRGWzy7wdR-mjmzuipqkV2SxzfJ9695Jf-xKlwDu8os2TUsWzUKF-Ac7AtHsDAc_2RjP7tWeQnGXMoVS_K4qJMnJQ98L3c-ZLi5JMqpSCv95s8VzLSl-i9do5ntKF9Dq06kDTnPCtzHj7oM-_gl8PXanuk0u-auQrk9CEhpFrV6YZ5Q4CgzrAATaBM9vSUnUUioxJf0nKoAdwmtdXgjdAU9UeCKEkGU2EtbGbszY1VxhGYpcNptYhP1LUAegLy-H9y_vVaTMxAcU8kvqs8rf3RLufVuIy2q0hKybVCQyS7a1hbCvnKEPbTBs320U9blwBqmD9Ctn-GOX-CGX-C5wKVf4DTDtV9g7ReHaPowntwFhq6UYSQWdXPDHokkGpkMyKbnMRbRhLpSyc-MgKAxR8RDMuKmzVgCfJEQi_LYoTK42XPhOYeTI9TL5hk_RtiymUPsJI6KlbvpxcKGmxhlMHYRi80BuioHJVwoQZRwpRkGyGkOW5gXu1BClYwJycrnTtbp5BRt1R58hnr5xxc_B6aYxxfa-j9_0WME |
| link.rule.ids | 315,783,787,27936,27937 |
| linkProvider | Library Specific Holdings |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=An+action-oriented+perspective+of+learning+in+classifier+systems&rft.jtitle=Journal+of+experimental+%26+theoretical+artificial+intelligence&rft.au=WEIss%2C+GERHARD&rft.date=1996-01-01&rft.issn=0952-813X&rft.eissn=1362-3079&rft.volume=8&rft.issue=1&rft.spage=43&rft.epage=62&rft_id=info:doi/10.1080%2F09528139650042538&rft.externalDBID=n%2Fa&rft.externalDocID=10_1080_09528139650042538 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0952-813X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0952-813X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0952-813X&client=summon |