Model selection in reinforcement learning View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2011-12

AUTHORS

Amir-massoud Farahmand, Csaba Szepesvári

ABSTRACT

We consider the problem of model selection in the batch (offline, non-interactive) reinforcement learning setting when the goal is to find an action-value function with the smallest Bellman error among a countable set of candidates functions. We propose a complexity regularization-based model selection algorithm, , and prove that it enjoys an oracle-like property: the estimator’s error differs from that of an oracle, who selects the candidate with the minimum Bellman error, by only a constant factor and a small remainder term that vanishes at a parametric rate as the number of samples increases. As an application, we consider a problem when the true action-value function belongs to an unknown member of a nested sequence of function spaces. We show that under some additional technical conditions leads to a procedure whose rate of convergence, up to a constant factor, matches that of an oracle who knows which of the nested function spaces the true action-value function belongs to, i.e., the procedure achieves adaptivity. More... »

PAGES

299-332

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s10994-011-5254-7

DOI

http://dx.doi.org/10.1007/s10994-011-5254-7

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1020927139


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 Alberta", 
          "id": "https://www.grid.ac/institutes/grid.17089.37", 
          "name": [
            "Department of Computing Science, University of Alberta, T6G 2E8, Edmonton, Canada"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Farahmand", 
        "givenName": "Amir-massoud", 
        "id": "sg:person.016600353731.42", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016600353731.42"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Alberta", 
          "id": "https://www.grid.ac/institutes/grid.17089.37", 
          "name": [
            "Department of Computing Science, University of Alberta, T6G 2E8, Edmonton, Canada"
          ], 
          "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"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1145/1553374.1553504", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1003071186"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1553374.1553442", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004258673"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1524/stnd.2006.24.3.351", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1008866674"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-94-011-3222-0_42", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009331800", 
          "https://doi.org/10.1007/978-94-011-3222-0_42"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-94-011-3222-0_42", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009331800", 
          "https://doi.org/10.1007/978-94-011-3222-0_42"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://app.dimensions.ai/details/publication/pub.1020741261", 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/b97848", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1020741261", 
          "https://doi.org/10.1007/b97848"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/b97848", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1020741261", 
          "https://doi.org/10.1007/b97848"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1013999503812", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025760069", 
          "https://doi.org/10.1023/a:1013999503812"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1143844.1143901", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1027219183"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10479-005-5732-z", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1027867003", 
          "https://doi.org/10.1007/s10479-005-5732-z"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10479-005-5732-z", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1027867003", 
          "https://doi.org/10.1007/s10479-005-5732-z"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1273496.1273589", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1028417234"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1007602715810", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1033709686", 
          "https://doi.org/10.1023/a:1007602715810"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10994-007-5038-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1036492501", 
          "https://doi.org/10.1007/s10994-007-5038-2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1102351.1102377", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051712050"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/11564096_32", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052945304", 
          "https://doi.org/10.1007/11564096_32"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/11564096_32", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052945304", 
          "https://doi.org/10.1007/11564096_32"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/18.650998", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061100555"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tnn.2007.899161", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061717231"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1214/009053604000000463", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1064388724"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1214/009053605000000282", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1064388814"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1214/09-ss054", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1064391087"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1214/aop/1019160125", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1064402878"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1214/aos/1046294464", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1064406408"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2200/s00268ed1v01y201005aim009", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1069288150"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/acc.2009.5160611", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093712090"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/adprl.2007.368210", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094742667"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/adprl.2007.368207", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095458992"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1017/cbo9780511626630", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1098694106"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2011-12", 
    "datePublishedReg": "2011-12-01", 
    "description": "We consider the problem of model selection in the batch (offline, non-interactive) reinforcement learning setting when the goal is to find an action-value function with the smallest Bellman error among a countable set of candidates functions. We propose a complexity regularization-based model selection algorithm, , and prove that it enjoys an oracle-like property: the estimator\u2019s error differs from that of an oracle, who selects the candidate with the minimum Bellman error, by only a constant factor and a small remainder term that vanishes at a parametric rate as the number of samples increases. As an application, we consider a problem when the true action-value function belongs to an unknown member of a nested sequence of function spaces. We show that under some additional technical conditions leads to a procedure whose rate of convergence, up to a constant factor, matches that of an oracle who knows which of the nested function spaces the true action-value function belongs to, i.e., the procedure achieves adaptivity.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s10994-011-5254-7", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1125588", 
        "issn": [
          "0885-6125", 
          "1573-0565"
        ], 
        "name": "Machine Learning", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "3", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "85"
      }
    ], 
    "name": "Model selection in reinforcement learning", 
    "pagination": "299-332", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "63b5838791eba2a34de5c1599832e889a6283ce227c4be73024d29f626a95b92"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s10994-011-5254-7"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1020927139"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s10994-011-5254-7", 
      "https://app.dimensions.ai/details/publication/pub.1020927139"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-10T23:24", 
    "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_8693_00000512.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "http://link.springer.com/10.1007%2Fs10994-011-5254-7"
  }
]
 

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.10.1007/s10994-011-5254-7'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s10994-011-5254-7'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s10994-011-5254-7'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s10994-011-5254-7'


 

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

152 TRIPLES      21 PREDICATES      53 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s10994-011-5254-7 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N83ff38038ca14ed28085522203eb14b1
4 schema:citation sg:pub.10.1007/11564096_32
5 sg:pub.10.1007/978-94-011-3222-0_42
6 sg:pub.10.1007/b97848
7 sg:pub.10.1007/s10479-005-5732-z
8 sg:pub.10.1007/s10994-007-5038-2
9 sg:pub.10.1023/a:1007602715810
10 sg:pub.10.1023/a:1013999503812
11 https://app.dimensions.ai/details/publication/pub.1020741261
12 https://doi.org/10.1017/cbo9780511626630
13 https://doi.org/10.1109/18.650998
14 https://doi.org/10.1109/acc.2009.5160611
15 https://doi.org/10.1109/adprl.2007.368207
16 https://doi.org/10.1109/adprl.2007.368210
17 https://doi.org/10.1109/tnn.2007.899161
18 https://doi.org/10.1145/1102351.1102377
19 https://doi.org/10.1145/1143844.1143901
20 https://doi.org/10.1145/1273496.1273589
21 https://doi.org/10.1145/1553374.1553442
22 https://doi.org/10.1145/1553374.1553504
23 https://doi.org/10.1214/009053604000000463
24 https://doi.org/10.1214/009053605000000282
25 https://doi.org/10.1214/09-ss054
26 https://doi.org/10.1214/aop/1019160125
27 https://doi.org/10.1214/aos/1046294464
28 https://doi.org/10.1524/stnd.2006.24.3.351
29 https://doi.org/10.2200/s00268ed1v01y201005aim009
30 schema:datePublished 2011-12
31 schema:datePublishedReg 2011-12-01
32 schema:description We consider the problem of model selection in the batch (offline, non-interactive) reinforcement learning setting when the goal is to find an action-value function with the smallest Bellman error among a countable set of candidates functions. We propose a complexity regularization-based model selection algorithm, , and prove that it enjoys an oracle-like property: the estimator’s error differs from that of an oracle, who selects the candidate with the minimum Bellman error, by only a constant factor and a small remainder term that vanishes at a parametric rate as the number of samples increases. As an application, we consider a problem when the true action-value function belongs to an unknown member of a nested sequence of function spaces. We show that under some additional technical conditions leads to a procedure whose rate of convergence, up to a constant factor, matches that of an oracle who knows which of the nested function spaces the true action-value function belongs to, i.e., the procedure achieves adaptivity.
33 schema:genre research_article
34 schema:inLanguage en
35 schema:isAccessibleForFree true
36 schema:isPartOf N39f655a6385742dbbe686416c0a87531
37 N3abd5ae396e545eb9768f79ab4ed1289
38 sg:journal.1125588
39 schema:name Model selection in reinforcement learning
40 schema:pagination 299-332
41 schema:productId N27d8da370f6a42598233444f8704bcff
42 N44a4434632214da68254f092a9d97d9b
43 Na99d9dd86cc24ec29aa5a5dbdccb4127
44 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020927139
45 https://doi.org/10.1007/s10994-011-5254-7
46 schema:sdDatePublished 2019-04-10T23:24
47 schema:sdLicense https://scigraph.springernature.com/explorer/license/
48 schema:sdPublisher N42b898df94e241a3b92a2c7f8f5d0562
49 schema:url http://link.springer.com/10.1007%2Fs10994-011-5254-7
50 sgo:license sg:explorer/license/
51 sgo:sdDataset articles
52 rdf:type schema:ScholarlyArticle
53 N27d8da370f6a42598233444f8704bcff schema:name readcube_id
54 schema:value 63b5838791eba2a34de5c1599832e889a6283ce227c4be73024d29f626a95b92
55 rdf:type schema:PropertyValue
56 N39f655a6385742dbbe686416c0a87531 schema:volumeNumber 85
57 rdf:type schema:PublicationVolume
58 N3abd5ae396e545eb9768f79ab4ed1289 schema:issueNumber 3
59 rdf:type schema:PublicationIssue
60 N42b898df94e241a3b92a2c7f8f5d0562 schema:name Springer Nature - SN SciGraph project
61 rdf:type schema:Organization
62 N44a4434632214da68254f092a9d97d9b schema:name doi
63 schema:value 10.1007/s10994-011-5254-7
64 rdf:type schema:PropertyValue
65 N83ff38038ca14ed28085522203eb14b1 rdf:first sg:person.016600353731.42
66 rdf:rest N9a77758f0f824555845743644ee22f9d
67 N9a77758f0f824555845743644ee22f9d rdf:first sg:person.016202177221.23
68 rdf:rest rdf:nil
69 Na99d9dd86cc24ec29aa5a5dbdccb4127 schema:name dimensions_id
70 schema:value pub.1020927139
71 rdf:type schema:PropertyValue
72 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
73 schema:name Information and Computing Sciences
74 rdf:type schema:DefinedTerm
75 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
76 schema:name Artificial Intelligence and Image Processing
77 rdf:type schema:DefinedTerm
78 sg:journal.1125588 schema:issn 0885-6125
79 1573-0565
80 schema:name Machine Learning
81 rdf:type schema:Periodical
82 sg:person.016202177221.23 schema:affiliation https://www.grid.ac/institutes/grid.17089.37
83 schema:familyName Szepesvári
84 schema:givenName Csaba
85 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016202177221.23
86 rdf:type schema:Person
87 sg:person.016600353731.42 schema:affiliation https://www.grid.ac/institutes/grid.17089.37
88 schema:familyName Farahmand
89 schema:givenName Amir-massoud
90 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016600353731.42
91 rdf:type schema:Person
92 sg:pub.10.1007/11564096_32 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052945304
93 https://doi.org/10.1007/11564096_32
94 rdf:type schema:CreativeWork
95 sg:pub.10.1007/978-94-011-3222-0_42 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009331800
96 https://doi.org/10.1007/978-94-011-3222-0_42
97 rdf:type schema:CreativeWork
98 sg:pub.10.1007/b97848 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020741261
99 https://doi.org/10.1007/b97848
100 rdf:type schema:CreativeWork
101 sg:pub.10.1007/s10479-005-5732-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1027867003
102 https://doi.org/10.1007/s10479-005-5732-z
103 rdf:type schema:CreativeWork
104 sg:pub.10.1007/s10994-007-5038-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036492501
105 https://doi.org/10.1007/s10994-007-5038-2
106 rdf:type schema:CreativeWork
107 sg:pub.10.1023/a:1007602715810 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033709686
108 https://doi.org/10.1023/a:1007602715810
109 rdf:type schema:CreativeWork
110 sg:pub.10.1023/a:1013999503812 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025760069
111 https://doi.org/10.1023/a:1013999503812
112 rdf:type schema:CreativeWork
113 https://app.dimensions.ai/details/publication/pub.1020741261 schema:CreativeWork
114 https://doi.org/10.1017/cbo9780511626630 schema:sameAs https://app.dimensions.ai/details/publication/pub.1098694106
115 rdf:type schema:CreativeWork
116 https://doi.org/10.1109/18.650998 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061100555
117 rdf:type schema:CreativeWork
118 https://doi.org/10.1109/acc.2009.5160611 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093712090
119 rdf:type schema:CreativeWork
120 https://doi.org/10.1109/adprl.2007.368207 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095458992
121 rdf:type schema:CreativeWork
122 https://doi.org/10.1109/adprl.2007.368210 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094742667
123 rdf:type schema:CreativeWork
124 https://doi.org/10.1109/tnn.2007.899161 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061717231
125 rdf:type schema:CreativeWork
126 https://doi.org/10.1145/1102351.1102377 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051712050
127 rdf:type schema:CreativeWork
128 https://doi.org/10.1145/1143844.1143901 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027219183
129 rdf:type schema:CreativeWork
130 https://doi.org/10.1145/1273496.1273589 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028417234
131 rdf:type schema:CreativeWork
132 https://doi.org/10.1145/1553374.1553442 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004258673
133 rdf:type schema:CreativeWork
134 https://doi.org/10.1145/1553374.1553504 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003071186
135 rdf:type schema:CreativeWork
136 https://doi.org/10.1214/009053604000000463 schema:sameAs https://app.dimensions.ai/details/publication/pub.1064388724
137 rdf:type schema:CreativeWork
138 https://doi.org/10.1214/009053605000000282 schema:sameAs https://app.dimensions.ai/details/publication/pub.1064388814
139 rdf:type schema:CreativeWork
140 https://doi.org/10.1214/09-ss054 schema:sameAs https://app.dimensions.ai/details/publication/pub.1064391087
141 rdf:type schema:CreativeWork
142 https://doi.org/10.1214/aop/1019160125 schema:sameAs https://app.dimensions.ai/details/publication/pub.1064402878
143 rdf:type schema:CreativeWork
144 https://doi.org/10.1214/aos/1046294464 schema:sameAs https://app.dimensions.ai/details/publication/pub.1064406408
145 rdf:type schema:CreativeWork
146 https://doi.org/10.1524/stnd.2006.24.3.351 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008866674
147 rdf:type schema:CreativeWork
148 https://doi.org/10.2200/s00268ed1v01y201005aim009 schema:sameAs https://app.dimensions.ai/details/publication/pub.1069288150
149 rdf:type schema:CreativeWork
150 https://www.grid.ac/institutes/grid.17089.37 schema:alternateName University of Alberta
151 schema:name Department of Computing Science, University of Alberta, T6G 2E8, Edmonton, Canada
152 rdf:type schema:Organization
 




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


...