Module-Based Reinforcement Learning: Experiments with a Real Robot View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

1998-07

AUTHORS

Zsolt Kalmár, Csaba Szepesvári, András Lőrincz

ABSTRACT

The behavior of reinforcement learning (RL) algorithms is best understood in completely observable, discrete-time controlled Markov chains with finite state and action spaces. In contrast, robot-learning domains are inherently continuous both in time and space, and moreover are partially observable. Here we suggest a systematic approach to solve such problems in which the available qualitative and quantitative knowledge is used to reduce the complexity of learning task. The steps of the design process are to: (i) decompose the task into subtasks using the qualitative knowledge at hand; (ii) design local controllers to solve the subtasks using the available quantitative knowledge, and (iii) learn a coordination of these controllers by means of reinforcement learning. It is argued that the approach enables fast, semi-automatic, but still high quality robot-control as no fine-tuning of the local controllers is needed. The approach was verified on a non-trivial real-life robot task. Several RL algorithms were compared by ANOVA and it was found that the model-based approach worked significantly better than the model-free approach. The learnt switching strategy performed comparably to a handcrafted version. Moreover, the learnt strategy seemed to exploit certain properties of the environment which were not foreseen in advance, thus supporting the view that adaptive algorithms are advantageous to nonadaptive ones in complex environments. More... »

PAGES

273-295

Identifiers

URI

http://scigraph.springernature.com/pub.10.1023/a:1008858222277

DOI

http://dx.doi.org/10.1023/a:1008858222277

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1007996845


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "University of Szeged", 
          "id": "https://www.grid.ac/institutes/grid.9008.1", 
          "name": [
            "Department of Informatics, \u201cJ\u00f3zsef Attila\u201d, University of Szeged, Aradi vrt. tere 1, H-6720, Szeged, Hungary"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kalm\u00e1r", 
        "givenName": "Zsolt", 
        "id": "sg:person.010745541621.05", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010745541621.05"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Research Group on Artificial Intelligence, \u201cJ\u00f3zsef Attila\u201d, Uni versity of Szeged, Aradi vrt. tere 1, H-6720, Szeged, Hungary"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Szepesv\u00e1ri", 
        "givenName": "Csaba", 
        "id": "sg:person.016202177221.23", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016202177221.23"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Szeged", 
          "id": "https://www.grid.ac/institutes/grid.9008.1", 
          "name": [
            "Department of Adaptive Systems, \u201cJ\u00f3zsef Attila\u201d, University of Szeged, Aradi vrt. tere 1, H-6720, Szeged, Hungary"
          ], 
          "type": "Organization"
        }, 
        "familyName": "L\u0151rincz", 
        "givenName": "Andr\u00e1s", 
        "id": "sg:person.0651500301.38", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0651500301.38"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/0004-3702(92)90058-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009445883"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(92)90058-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009445883"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1177/105971239300200202", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1011632542"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1177/105971239300200202", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1011632542"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0004-3702(97)00024-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1014535345"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00117447", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1016428696", 
          "https://doi.org/10.1007/bf00117447"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00199056", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1020476341", 
          "https://doi.org/10.1007/bf00199056"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00199056", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1020476341", 
          "https://doi.org/10.1007/bf00199056"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(74)90026-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022737316"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(74)90026-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022737316"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-1-4757-6451-2_4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1027090828", 
          "https://doi.org/10.1007/978-1-4757-6451-2_4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/b978-1-55860-307-3.50031-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1027483934"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-1-4612-0313-1_2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1028591645", 
          "https://doi.org/10.1007/978-1-4612-0313-1_2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-1-4612-0313-1_2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1028591645", 
          "https://doi.org/10.1007/978-1-4612-0313-1_2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(94)90047-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030423455"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(94)90047-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030423455"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(87)90051-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1032263079"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(87)90051-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1032263079"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00992698", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1033088958", 
          "https://doi.org/10.1007/bf00992698"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/neco.1994.6.6.1185", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1037933600"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(85)90012-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040890145"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(85)90012-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040890145"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(94)00011-o", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1043559588"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-62858-4_89", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044902459", 
          "https://doi.org/10.1007/3-540-62858-4_89"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-62858-4_82", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1047524411", 
          "https://doi.org/10.1007/3-540-62858-4_82"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00114728", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1048017946", 
          "https://doi.org/10.1007/bf00114728"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(84)90037-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050744239"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(84)90037-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050744239"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00114724", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051613972", 
          "https://doi.org/10.1007/bf00114724"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(95)00016-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051706335"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00996270", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053528809", 
          "https://doi.org/10.1007/bf00996270"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/3477.499789", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061158049"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1137/0321030", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062843696"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1137/0323023", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062843811"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.4064/sm-45-2-161-171", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091815224"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icnn.1994.374432", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094331265"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icnn.1994.374418", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094588738"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iros.1996.568989", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095624088"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1613/jair.301", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1105538429"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "1998-07", 
    "datePublishedReg": "1998-07-01", 
    "description": "The behavior of reinforcement learning (RL) algorithms is best understood in completely observable, discrete-time controlled Markov chains with finite state and action spaces. In contrast, robot-learning domains are inherently continuous both in time and space, and moreover are partially observable. Here we suggest a systematic approach to solve such problems in which the available qualitative and quantitative knowledge is used to reduce the complexity of learning task. The steps of the design process are to: (i) decompose the task into subtasks using the qualitative knowledge at hand; (ii) design local controllers to solve the subtasks using the available quantitative knowledge, and (iii) learn a coordination of these controllers by means of reinforcement learning. It is argued that the approach enables fast, semi-automatic, but still high quality robot-control as no fine-tuning of the local controllers is needed. The approach was verified on a non-trivial real-life robot task. Several RL algorithms were compared by ANOVA and it was found that the model-based approach worked significantly better than the model-free approach. The learnt switching strategy performed comparably to a handcrafted version. Moreover, the learnt strategy seemed to exploit certain properties of the environment which were not foreseen in advance, thus supporting the view that adaptive algorithms are advantageous to nonadaptive ones in complex environments.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1023/a:1008858222277", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1031086", 
        "issn": [
          "0929-5593", 
          "1573-7527"
        ], 
        "name": "Autonomous Robots", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "3-4", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "5"
      }
    ], 
    "name": "Module-Based Reinforcement Learning: Experiments with a Real Robot", 
    "pagination": "273-295", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "26191283d34e578492d0ee0e2e2655bb1cfee3dd094a81df1717c639a6267d75"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1023/a:1008858222277"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1007996845"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1023/a:1008858222277", 
      "https://app.dimensions.ai/details/publication/pub.1007996845"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-10T14:06", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8660_00000498.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "http://link.springer.com/10.1023/A:1008858222277"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1023/a:1008858222277'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1023/a:1008858222277'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1023/a:1008858222277'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1023/a:1008858222277'


 

This table displays all metadata directly associated to this object as RDF triples.

178 TRIPLES      21 PREDICATES      57 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1023/a:1008858222277 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N0fabdb3c3f1448c0b384585bddeeac90
4 schema:citation sg:pub.10.1007/3-540-62858-4_82
5 sg:pub.10.1007/3-540-62858-4_89
6 sg:pub.10.1007/978-1-4612-0313-1_2
7 sg:pub.10.1007/978-1-4757-6451-2_4
8 sg:pub.10.1007/bf00114724
9 sg:pub.10.1007/bf00114728
10 sg:pub.10.1007/bf00117447
11 sg:pub.10.1007/bf00199056
12 sg:pub.10.1007/bf00992698
13 sg:pub.10.1007/bf00996270
14 https://doi.org/10.1016/0004-3702(74)90026-5
15 https://doi.org/10.1016/0004-3702(84)90037-7
16 https://doi.org/10.1016/0004-3702(85)90012-8
17 https://doi.org/10.1016/0004-3702(87)90051-8
18 https://doi.org/10.1016/0004-3702(92)90058-6
19 https://doi.org/10.1016/0004-3702(94)00011-o
20 https://doi.org/10.1016/0004-3702(94)90047-7
21 https://doi.org/10.1016/0004-3702(95)00016-x
22 https://doi.org/10.1016/b978-1-55860-307-3.50031-9
23 https://doi.org/10.1016/s0004-3702(97)00024-6
24 https://doi.org/10.1109/3477.499789
25 https://doi.org/10.1109/icnn.1994.374418
26 https://doi.org/10.1109/icnn.1994.374432
27 https://doi.org/10.1109/iros.1996.568989
28 https://doi.org/10.1137/0321030
29 https://doi.org/10.1137/0323023
30 https://doi.org/10.1162/neco.1994.6.6.1185
31 https://doi.org/10.1177/105971239300200202
32 https://doi.org/10.1613/jair.301
33 https://doi.org/10.4064/sm-45-2-161-171
34 schema:datePublished 1998-07
35 schema:datePublishedReg 1998-07-01
36 schema:description The behavior of reinforcement learning (RL) algorithms is best understood in completely observable, discrete-time controlled Markov chains with finite state and action spaces. In contrast, robot-learning domains are inherently continuous both in time and space, and moreover are partially observable. Here we suggest a systematic approach to solve such problems in which the available qualitative and quantitative knowledge is used to reduce the complexity of learning task. The steps of the design process are to: (i) decompose the task into subtasks using the qualitative knowledge at hand; (ii) design local controllers to solve the subtasks using the available quantitative knowledge, and (iii) learn a coordination of these controllers by means of reinforcement learning. It is argued that the approach enables fast, semi-automatic, but still high quality robot-control as no fine-tuning of the local controllers is needed. The approach was verified on a non-trivial real-life robot task. Several RL algorithms were compared by ANOVA and it was found that the model-based approach worked significantly better than the model-free approach. The learnt switching strategy performed comparably to a handcrafted version. Moreover, the learnt strategy seemed to exploit certain properties of the environment which were not foreseen in advance, thus supporting the view that adaptive algorithms are advantageous to nonadaptive ones in complex environments.
37 schema:genre research_article
38 schema:inLanguage en
39 schema:isAccessibleForFree false
40 schema:isPartOf N801bc9f8b8964ebe9368db1ccb3111d8
41 Nc756fa5b8e894927aa11892ba1b16b97
42 sg:journal.1031086
43 schema:name Module-Based Reinforcement Learning: Experiments with a Real Robot
44 schema:pagination 273-295
45 schema:productId Nd7b129dd3eb447918e8f56ffdf034229
46 Nd938deed9e8344eca67dcd20a004a330
47 Nf2eda1ec46c3435ca5fd939b9e8b32ca
48 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007996845
49 https://doi.org/10.1023/a:1008858222277
50 schema:sdDatePublished 2019-04-10T14:06
51 schema:sdLicense https://scigraph.springernature.com/explorer/license/
52 schema:sdPublisher N64cf61d8372248d89e7d31b0334fa7ea
53 schema:url http://link.springer.com/10.1023/A:1008858222277
54 sgo:license sg:explorer/license/
55 sgo:sdDataset articles
56 rdf:type schema:ScholarlyArticle
57 N0fabdb3c3f1448c0b384585bddeeac90 rdf:first sg:person.010745541621.05
58 rdf:rest N790eed32972144a5b1aca8c00047eaaf
59 N2a3ef43eb16d4184b2d4d2c269c2eb1f rdf:first sg:person.0651500301.38
60 rdf:rest rdf:nil
61 N5bb70f8176ff429da0d71423cd1345a6 schema:name Research Group on Artificial Intelligence, “József Attila”, Uni versity of Szeged, Aradi vrt. tere 1, H-6720, Szeged, Hungary
62 rdf:type schema:Organization
63 N64cf61d8372248d89e7d31b0334fa7ea schema:name Springer Nature - SN SciGraph project
64 rdf:type schema:Organization
65 N790eed32972144a5b1aca8c00047eaaf rdf:first sg:person.016202177221.23
66 rdf:rest N2a3ef43eb16d4184b2d4d2c269c2eb1f
67 N801bc9f8b8964ebe9368db1ccb3111d8 schema:volumeNumber 5
68 rdf:type schema:PublicationVolume
69 Nc756fa5b8e894927aa11892ba1b16b97 schema:issueNumber 3-4
70 rdf:type schema:PublicationIssue
71 Nd7b129dd3eb447918e8f56ffdf034229 schema:name readcube_id
72 schema:value 26191283d34e578492d0ee0e2e2655bb1cfee3dd094a81df1717c639a6267d75
73 rdf:type schema:PropertyValue
74 Nd938deed9e8344eca67dcd20a004a330 schema:name doi
75 schema:value 10.1023/a:1008858222277
76 rdf:type schema:PropertyValue
77 Nf2eda1ec46c3435ca5fd939b9e8b32ca schema:name dimensions_id
78 schema:value pub.1007996845
79 rdf:type schema:PropertyValue
80 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
81 schema:name Information and Computing Sciences
82 rdf:type schema:DefinedTerm
83 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
84 schema:name Artificial Intelligence and Image Processing
85 rdf:type schema:DefinedTerm
86 sg:journal.1031086 schema:issn 0929-5593
87 1573-7527
88 schema:name Autonomous Robots
89 rdf:type schema:Periodical
90 sg:person.010745541621.05 schema:affiliation https://www.grid.ac/institutes/grid.9008.1
91 schema:familyName Kalmár
92 schema:givenName Zsolt
93 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010745541621.05
94 rdf:type schema:Person
95 sg:person.016202177221.23 schema:affiliation N5bb70f8176ff429da0d71423cd1345a6
96 schema:familyName Szepesvári
97 schema:givenName Csaba
98 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016202177221.23
99 rdf:type schema:Person
100 sg:person.0651500301.38 schema:affiliation https://www.grid.ac/institutes/grid.9008.1
101 schema:familyName Lőrincz
102 schema:givenName András
103 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0651500301.38
104 rdf:type schema:Person
105 sg:pub.10.1007/3-540-62858-4_82 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047524411
106 https://doi.org/10.1007/3-540-62858-4_82
107 rdf:type schema:CreativeWork
108 sg:pub.10.1007/3-540-62858-4_89 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044902459
109 https://doi.org/10.1007/3-540-62858-4_89
110 rdf:type schema:CreativeWork
111 sg:pub.10.1007/978-1-4612-0313-1_2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028591645
112 https://doi.org/10.1007/978-1-4612-0313-1_2
113 rdf:type schema:CreativeWork
114 sg:pub.10.1007/978-1-4757-6451-2_4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027090828
115 https://doi.org/10.1007/978-1-4757-6451-2_4
116 rdf:type schema:CreativeWork
117 sg:pub.10.1007/bf00114724 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051613972
118 https://doi.org/10.1007/bf00114724
119 rdf:type schema:CreativeWork
120 sg:pub.10.1007/bf00114728 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048017946
121 https://doi.org/10.1007/bf00114728
122 rdf:type schema:CreativeWork
123 sg:pub.10.1007/bf00117447 schema:sameAs https://app.dimensions.ai/details/publication/pub.1016428696
124 https://doi.org/10.1007/bf00117447
125 rdf:type schema:CreativeWork
126 sg:pub.10.1007/bf00199056 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020476341
127 https://doi.org/10.1007/bf00199056
128 rdf:type schema:CreativeWork
129 sg:pub.10.1007/bf00992698 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033088958
130 https://doi.org/10.1007/bf00992698
131 rdf:type schema:CreativeWork
132 sg:pub.10.1007/bf00996270 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053528809
133 https://doi.org/10.1007/bf00996270
134 rdf:type schema:CreativeWork
135 https://doi.org/10.1016/0004-3702(74)90026-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022737316
136 rdf:type schema:CreativeWork
137 https://doi.org/10.1016/0004-3702(84)90037-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050744239
138 rdf:type schema:CreativeWork
139 https://doi.org/10.1016/0004-3702(85)90012-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040890145
140 rdf:type schema:CreativeWork
141 https://doi.org/10.1016/0004-3702(87)90051-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032263079
142 rdf:type schema:CreativeWork
143 https://doi.org/10.1016/0004-3702(92)90058-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009445883
144 rdf:type schema:CreativeWork
145 https://doi.org/10.1016/0004-3702(94)00011-o schema:sameAs https://app.dimensions.ai/details/publication/pub.1043559588
146 rdf:type schema:CreativeWork
147 https://doi.org/10.1016/0004-3702(94)90047-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030423455
148 rdf:type schema:CreativeWork
149 https://doi.org/10.1016/0004-3702(95)00016-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1051706335
150 rdf:type schema:CreativeWork
151 https://doi.org/10.1016/b978-1-55860-307-3.50031-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027483934
152 rdf:type schema:CreativeWork
153 https://doi.org/10.1016/s0004-3702(97)00024-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014535345
154 rdf:type schema:CreativeWork
155 https://doi.org/10.1109/3477.499789 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061158049
156 rdf:type schema:CreativeWork
157 https://doi.org/10.1109/icnn.1994.374418 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094588738
158 rdf:type schema:CreativeWork
159 https://doi.org/10.1109/icnn.1994.374432 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094331265
160 rdf:type schema:CreativeWork
161 https://doi.org/10.1109/iros.1996.568989 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095624088
162 rdf:type schema:CreativeWork
163 https://doi.org/10.1137/0321030 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062843696
164 rdf:type schema:CreativeWork
165 https://doi.org/10.1137/0323023 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062843811
166 rdf:type schema:CreativeWork
167 https://doi.org/10.1162/neco.1994.6.6.1185 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037933600
168 rdf:type schema:CreativeWork
169 https://doi.org/10.1177/105971239300200202 schema:sameAs https://app.dimensions.ai/details/publication/pub.1011632542
170 rdf:type schema:CreativeWork
171 https://doi.org/10.1613/jair.301 schema:sameAs https://app.dimensions.ai/details/publication/pub.1105538429
172 rdf:type schema:CreativeWork
173 https://doi.org/10.4064/sm-45-2-161-171 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091815224
174 rdf:type schema:CreativeWork
175 https://www.grid.ac/institutes/grid.9008.1 schema:alternateName University of Szeged
176 schema:name Department of Adaptive Systems, “József Attila”, University of Szeged, Aradi vrt. tere 1, H-6720, Szeged, Hungary
177 Department of Informatics, “József Attila”, University of Szeged, Aradi vrt. tere 1, H-6720, Szeged, Hungary
178 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...