Human-level control through deep reinforcement learning View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2015-02

AUTHORS

Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, Demis Hassabis

ABSTRACT

The theory of reinforcement learning provides a normative account, deeply rooted in psychological and neuroscientific perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems, the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms. While reinforcement learning agents have achieved some successes in a variety of domains, their applicability has previously been limited to domains in which useful features can be handcrafted, or to domains with fully observed, low-dimensional state spaces. Here we use recent advances in training deep neural networks to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. We tested this agent on the challenging domain of classic Atari 2600 games. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters. This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks. More... »

PAGES

529

Identifiers

URI

http://scigraph.springernature.com/pub.10.1038/nature14236

DOI

http://dx.doi.org/10.1038/nature14236

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1030517994

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/25719670


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"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Algorithms", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Artificial Intelligence", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Humans", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Models, Psychological", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Neural Networks (Computer)", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Reinforcement (Psychology)", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Reward", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Video Games", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Mnih", 
        "givenName": "Volodymyr", 
        "id": "sg:person.01324724017.03", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01324724017.03"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kavukcuoglu", 
        "givenName": "Koray", 
        "id": "sg:person.01354477236.72", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01354477236.72"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Silver", 
        "givenName": "David", 
        "id": "sg:person.0631073136.81", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0631073136.81"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Rusu", 
        "givenName": "Andrei A.", 
        "id": "sg:person.0604425216.82", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0604425216.82"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Veness", 
        "givenName": "Joel", 
        "id": "sg:person.0745321536.28", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0745321536.28"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Bellemare", 
        "givenName": "Marc G.", 
        "id": "sg:person.0703136271.51", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0703136271.51"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Graves", 
        "givenName": "Alex", 
        "id": "sg:person.01061550136.00", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01061550136.00"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Riedmiller", 
        "givenName": "Martin", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Fidjeland", 
        "givenName": "Andreas K.", 
        "id": "sg:person.013266321653.49", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013266321653.49"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ostrovski", 
        "givenName": "Georg", 
        "id": "sg:person.01244111736.76", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01244111736.76"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Petersen", 
        "givenName": "Stig", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Beattie", 
        "givenName": "Charles", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Sadik", 
        "givenName": "Amir", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Antonoglou", 
        "givenName": "Ioannis", 
        "id": "sg:person.0703047436.03", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0703047436.03"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "King", 
        "givenName": "Helen", 
        "id": "sg:person.0751162636.50", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0751162636.50"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kumaran", 
        "givenName": "Dharshan", 
        "id": "sg:person.01064217473.46", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01064217473.46"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wierstra", 
        "givenName": "Daan", 
        "id": "sg:person.010032372337.16", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010032372337.16"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Legg", 
        "givenName": "Shane", 
        "id": "sg:person.01133524436.96", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01133524436.96"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Google DeepMind, 5 New Street Square, London EC4A 3TW, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Hassabis", 
        "givenName": "Demis", 
        "id": "sg:person.0741767337.55", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0741767337.55"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/j.tins.2010.01.006", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1000486991"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1126/science.275.5306.1593", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1001523695"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1126/science.1127647", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004607132"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1390156.1390187", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1007561122"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1113/jphysiol.1963.sp007079", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009974284"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1037/0033-295x.102.3.419", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1014544738"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00344251", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1016635886", 
          "https://doi.org/10.1007/bf00344251"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10514-009-9120-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018478429", 
          "https://doi.org/10.1007/s10514-009-9120-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10514-009-9120-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018478429", 
          "https://doi.org/10.1007/s10514-009-9120-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10514-009-9120-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018478429", 
          "https://doi.org/10.1007/s10514-009-9120-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0004-3702(98)00023-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1020908447"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/415318a", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022954489", 
          "https://doi.org/10.1038/415318a"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/415318a", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022954489", 
          "https://doi.org/10.1038/415318a"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00993104", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026205858", 
          "https://doi.org/10.1007/bf00993104"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/nn.3203", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030841884", 
          "https://doi.org/10.1038/nn.3203"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/nn.2304", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044077421", 
          "https://doi.org/10.1038/nn.2304"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/nn.2304", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044077421", 
          "https://doi.org/10.1038/nn.2304"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11023-007-9079-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044356842", 
          "https://doi.org/10.1007/s11023-007-9079-x"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/203330.203343", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052366953"
        ], 
        "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/10.1109/5.726791", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061179979"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/9.580874", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061245225"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tnn.1998.712192", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061716400"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1561/2200000006", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1068001401"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2307/415721", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1070578988"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2009.5459469", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093416695"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/ijcnn.2010.5596468", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094389860"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2005.254", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095271325"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2005.254", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095271325"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1613/jair.3912", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1105689878"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2015-02", 
    "datePublishedReg": "2015-02-01", 
    "description": "The theory of reinforcement learning provides a normative account, deeply rooted in psychological and neuroscientific perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems, the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms. While reinforcement learning agents have achieved some successes in a variety of domains, their applicability has previously been limited to domains in which useful features can be handcrafted, or to domains with fully observed, low-dimensional state spaces. Here we use recent advances in training deep neural networks to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. We tested this agent on the challenging domain of classic Atari 2600 games. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters. This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks. ", 
    "genre": "research_article", 
    "id": "sg:pub.10.1038/nature14236", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1018957", 
        "issn": [
          "0090-0028", 
          "1476-4687"
        ], 
        "name": "Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "7540", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "518"
      }
    ], 
    "name": "Human-level control through deep reinforcement learning", 
    "pagination": "529", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "9162429e9c48d7c985e0b045d760a93bcd11f292cd7fd316e6c1e0a2c885449b"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "25719670"
        ]
      }, 
      {
        "name": "nlm_unique_id", 
        "type": "PropertyValue", 
        "value": [
          "0410462"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1038/nature14236"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1030517994"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1038/nature14236", 
      "https://app.dimensions.ai/details/publication/pub.1030517994"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T00:28", 
    "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_8695_00000588.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://www.nature.com/articles/nature14236"
  }
]
 

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.10.1038/nature14236'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1038/nature14236'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1038/nature14236'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1038/nature14236'


 

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

341 TRIPLES      21 PREDICATES      62 URIs      29 LITERALS      17 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1038/nature14236 schema:about N055f6735bb0d462f9578eff82ed7d517
2 N102e6be535614a839daada58c88fb831
3 N11722d14de0740738fcbed0e2fd74712
4 N48d7e3eeb991489aaa5cf6eecd9ac0c5
5 N969d5956aa5f494ba93033e5aad00394
6 Nad04723b21154c509f95f90076d28804
7 Nc256f573edd0486081a871f38f5ec5a7
8 Nf94a5797475049558bbd2cf49effc7ee
9 anzsrc-for:08
10 anzsrc-for:0801
11 schema:author N8b27974e61bf4faeacd46154c757d9b9
12 schema:citation sg:pub.10.1007/11564096_32
13 sg:pub.10.1007/bf00344251
14 sg:pub.10.1007/bf00993104
15 sg:pub.10.1007/s10514-009-9120-4
16 sg:pub.10.1007/s11023-007-9079-x
17 sg:pub.10.1038/415318a
18 sg:pub.10.1038/nn.2304
19 sg:pub.10.1038/nn.3203
20 https://doi.org/10.1016/j.tins.2010.01.006
21 https://doi.org/10.1016/s0004-3702(98)00023-x
22 https://doi.org/10.1037/0033-295x.102.3.419
23 https://doi.org/10.1109/5.726791
24 https://doi.org/10.1109/9.580874
25 https://doi.org/10.1109/cvpr.2005.254
26 https://doi.org/10.1109/iccv.2009.5459469
27 https://doi.org/10.1109/ijcnn.2010.5596468
28 https://doi.org/10.1109/tnn.1998.712192
29 https://doi.org/10.1113/jphysiol.1963.sp007079
30 https://doi.org/10.1126/science.1127647
31 https://doi.org/10.1126/science.275.5306.1593
32 https://doi.org/10.1145/1390156.1390187
33 https://doi.org/10.1145/203330.203343
34 https://doi.org/10.1561/2200000006
35 https://doi.org/10.1613/jair.3912
36 https://doi.org/10.2307/415721
37 schema:datePublished 2015-02
38 schema:datePublishedReg 2015-02-01
39 schema:description The theory of reinforcement learning provides a normative account, deeply rooted in psychological and neuroscientific perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems, the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms. While reinforcement learning agents have achieved some successes in a variety of domains, their applicability has previously been limited to domains in which useful features can be handcrafted, or to domains with fully observed, low-dimensional state spaces. Here we use recent advances in training deep neural networks to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. We tested this agent on the challenging domain of classic Atari 2600 games. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters. This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
40 schema:genre research_article
41 schema:inLanguage en
42 schema:isAccessibleForFree false
43 schema:isPartOf N2c8d6d2085b74183b9bf54d2524c8dcd
44 Ndbdb6f2654b14c00a2f73548780abcd5
45 sg:journal.1018957
46 schema:name Human-level control through deep reinforcement learning
47 schema:pagination 529
48 schema:productId N203d7cda480340d68a09af26adaccf1d
49 N3418f8df6bc1482e8c2c695deafd9c4a
50 N78939050076242d1a2c5895dd7f74e0a
51 Nb54b44a479b54dadad3bd675e5be8808
52 Nc68b3dfdbf4341e999a376d5c9e58048
53 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030517994
54 https://doi.org/10.1038/nature14236
55 schema:sdDatePublished 2019-04-11T00:28
56 schema:sdLicense https://scigraph.springernature.com/explorer/license/
57 schema:sdPublisher N2655968458bf4cbab19898a161ae81ec
58 schema:url https://www.nature.com/articles/nature14236
59 sgo:license sg:explorer/license/
60 sgo:sdDataset articles
61 rdf:type schema:ScholarlyArticle
62 N01a141d6f1c34cb09bc8b3e985d8dee6 rdf:first sg:person.0604425216.82
63 rdf:rest N295c9b0ae65049b29b85c01f43efcefd
64 N023840a494704e899f8a86ac1bedbfb4 rdf:first sg:person.010032372337.16
65 rdf:rest N63a9482a45f34ae48cad957c0efb398e
66 N055f6735bb0d462f9578eff82ed7d517 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
67 schema:name Neural Networks (Computer)
68 rdf:type schema:DefinedTerm
69 N095799d5c96e45bbbcbaeae476ab6de7 schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
70 rdf:type schema:Organization
71 N0cfc4cb4d2f54966962c758c18744a0d rdf:first sg:person.0703047436.03
72 rdf:rest N81b09b1d259a478b842117126836237b
73 N102e6be535614a839daada58c88fb831 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
74 schema:name Humans
75 rdf:type schema:DefinedTerm
76 N11722d14de0740738fcbed0e2fd74712 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
77 schema:name Reward
78 rdf:type schema:DefinedTerm
79 N1ca66dfde456443393a4d2bb25fc1ec7 schema:affiliation Nb30b6ac64cf44b06bc27bdd0610fd468
80 schema:familyName Riedmiller
81 schema:givenName Martin
82 rdf:type schema:Person
83 N1ccdbfe7062848df93ba68b5cbe80b4d rdf:first sg:person.01244111736.76
84 rdf:rest N5cc08dc68e3f4805b35a8036ca7e99a9
85 N203d7cda480340d68a09af26adaccf1d schema:name dimensions_id
86 schema:value pub.1030517994
87 rdf:type schema:PropertyValue
88 N22e7fa4286f84c5b9447540edb604d39 rdf:first N8aa46f43e58f4d82bc51c88e6da71d99
89 rdf:rest N0cfc4cb4d2f54966962c758c18744a0d
90 N2655968458bf4cbab19898a161ae81ec schema:name Springer Nature - SN SciGraph project
91 rdf:type schema:Organization
92 N295c9b0ae65049b29b85c01f43efcefd rdf:first sg:person.0745321536.28
93 rdf:rest Nad0d49e24c9b474a8608f9b6f624a95f
94 N2c8d6d2085b74183b9bf54d2524c8dcd schema:issueNumber 7540
95 rdf:type schema:PublicationIssue
96 N2dbd03c040b54110a2255ec3de4ef26c schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
97 rdf:type schema:Organization
98 N3401127d4e224e6cb79064f29f6e5ca7 schema:affiliation N345664cebb6c4cbe9a87623cf10ead4d
99 schema:familyName Beattie
100 schema:givenName Charles
101 rdf:type schema:Person
102 N3418f8df6bc1482e8c2c695deafd9c4a schema:name pubmed_id
103 schema:value 25719670
104 rdf:type schema:PropertyValue
105 N345664cebb6c4cbe9a87623cf10ead4d schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
106 rdf:type schema:Organization
107 N38b1df3fe27d42f998e4995cf5d598dd rdf:first sg:person.013266321653.49
108 rdf:rest N1ccdbfe7062848df93ba68b5cbe80b4d
109 N3a3aa7b536ed4f79858f6fcb870f8a8a schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
110 rdf:type schema:Organization
111 N3ff4bbfad0d2472cac3448ca40a26c8c rdf:first N1ca66dfde456443393a4d2bb25fc1ec7
112 rdf:rest N38b1df3fe27d42f998e4995cf5d598dd
113 N48d7e3eeb991489aaa5cf6eecd9ac0c5 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
114 schema:name Reinforcement (Psychology)
115 rdf:type schema:DefinedTerm
116 N52b6d9a1f12643aabb1cf31861e887d8 schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
117 rdf:type schema:Organization
118 N542fc21ada7547bda00c84741bdce940 schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
119 rdf:type schema:Organization
120 N5b38d4608b2042e8af01a45263d70924 rdf:first sg:person.0741767337.55
121 rdf:rest rdf:nil
122 N5cc08dc68e3f4805b35a8036ca7e99a9 rdf:first Nb3d2122ec4574ee1bb69468ad8f9c689
123 rdf:rest Nb95d27763c3448cfae8b8fb1472532f4
124 N63a9482a45f34ae48cad957c0efb398e rdf:first sg:person.01133524436.96
125 rdf:rest N5b38d4608b2042e8af01a45263d70924
126 N659efab71efd4a2984244a36f237b7e0 schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
127 rdf:type schema:Organization
128 N6caca14c13a444f390e77a6d2a8c256f schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
129 rdf:type schema:Organization
130 N78939050076242d1a2c5895dd7f74e0a schema:name doi
131 schema:value 10.1038/nature14236
132 rdf:type schema:PropertyValue
133 N81b09b1d259a478b842117126836237b rdf:first sg:person.0751162636.50
134 rdf:rest N96a079bd6d384899aba402ffe61d2330
135 N83df774e11f2413f8657139f7d629263 schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
136 rdf:type schema:Organization
137 N89913a8d97f04637b886eff689d94bd9 schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
138 rdf:type schema:Organization
139 N8aa46f43e58f4d82bc51c88e6da71d99 schema:affiliation N542fc21ada7547bda00c84741bdce940
140 schema:familyName Sadik
141 schema:givenName Amir
142 rdf:type schema:Person
143 N8b27974e61bf4faeacd46154c757d9b9 rdf:first sg:person.01324724017.03
144 rdf:rest Nbb968a1f306e4e79be29cb34a72dd881
145 N905fa635a9f84456b5083b4c46b86020 schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
146 rdf:type schema:Organization
147 N9228fcfc3326476cb565e88b3d1f76b3 schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
148 rdf:type schema:Organization
149 N93098500860e4dff985e2e3281e2a1b1 schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
150 rdf:type schema:Organization
151 N969d5956aa5f494ba93033e5aad00394 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
152 schema:name Algorithms
153 rdf:type schema:DefinedTerm
154 N96a079bd6d384899aba402ffe61d2330 rdf:first sg:person.01064217473.46
155 rdf:rest N023840a494704e899f8a86ac1bedbfb4
156 N9e32463de05446dd92fb99715d96c2a5 schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
157 rdf:type schema:Organization
158 Na92b5385b0a743e29d7b3e4b55fcdb4c schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
159 rdf:type schema:Organization
160 Nad04723b21154c509f95f90076d28804 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
161 schema:name Artificial Intelligence
162 rdf:type schema:DefinedTerm
163 Nad0d49e24c9b474a8608f9b6f624a95f rdf:first sg:person.0703136271.51
164 rdf:rest Nb6591f1f3c7441d18e86951b9b4da80c
165 Nb30b6ac64cf44b06bc27bdd0610fd468 schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
166 rdf:type schema:Organization
167 Nb3d2122ec4574ee1bb69468ad8f9c689 schema:affiliation N83df774e11f2413f8657139f7d629263
168 schema:familyName Petersen
169 schema:givenName Stig
170 rdf:type schema:Person
171 Nb54b44a479b54dadad3bd675e5be8808 schema:name readcube_id
172 schema:value 9162429e9c48d7c985e0b045d760a93bcd11f292cd7fd316e6c1e0a2c885449b
173 rdf:type schema:PropertyValue
174 Nb6591f1f3c7441d18e86951b9b4da80c rdf:first sg:person.01061550136.00
175 rdf:rest N3ff4bbfad0d2472cac3448ca40a26c8c
176 Nb95d27763c3448cfae8b8fb1472532f4 rdf:first N3401127d4e224e6cb79064f29f6e5ca7
177 rdf:rest N22e7fa4286f84c5b9447540edb604d39
178 Nbb968a1f306e4e79be29cb34a72dd881 rdf:first sg:person.01354477236.72
179 rdf:rest Ne1c19942b7f94e4f89334268ada5c394
180 Nc256f573edd0486081a871f38f5ec5a7 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
181 schema:name Video Games
182 rdf:type schema:DefinedTerm
183 Nc68b3dfdbf4341e999a376d5c9e58048 schema:name nlm_unique_id
184 schema:value 0410462
185 rdf:type schema:PropertyValue
186 Ncae4ec1c7def4077b7fdc60fb2dd09f7 schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
187 rdf:type schema:Organization
188 Ncca81628130249b0a41c243ed1fa7866 schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
189 rdf:type schema:Organization
190 Ndbdb6f2654b14c00a2f73548780abcd5 schema:volumeNumber 518
191 rdf:type schema:PublicationVolume
192 Ne026e61900b44ca7b87504182d03574b schema:name Google DeepMind, 5 New Street Square, London EC4A 3TW, UK
193 rdf:type schema:Organization
194 Ne1c19942b7f94e4f89334268ada5c394 rdf:first sg:person.0631073136.81
195 rdf:rest N01a141d6f1c34cb09bc8b3e985d8dee6
196 Nf94a5797475049558bbd2cf49effc7ee schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
197 schema:name Models, Psychological
198 rdf:type schema:DefinedTerm
199 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
200 schema:name Information and Computing Sciences
201 rdf:type schema:DefinedTerm
202 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
203 schema:name Artificial Intelligence and Image Processing
204 rdf:type schema:DefinedTerm
205 sg:journal.1018957 schema:issn 0090-0028
206 1476-4687
207 schema:name Nature
208 rdf:type schema:Periodical
209 sg:person.010032372337.16 schema:affiliation N9e32463de05446dd92fb99715d96c2a5
210 schema:familyName Wierstra
211 schema:givenName Daan
212 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010032372337.16
213 rdf:type schema:Person
214 sg:person.01061550136.00 schema:affiliation N659efab71efd4a2984244a36f237b7e0
215 schema:familyName Graves
216 schema:givenName Alex
217 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01061550136.00
218 rdf:type schema:Person
219 sg:person.01064217473.46 schema:affiliation N89913a8d97f04637b886eff689d94bd9
220 schema:familyName Kumaran
221 schema:givenName Dharshan
222 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01064217473.46
223 rdf:type schema:Person
224 sg:person.01133524436.96 schema:affiliation N93098500860e4dff985e2e3281e2a1b1
225 schema:familyName Legg
226 schema:givenName Shane
227 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01133524436.96
228 rdf:type schema:Person
229 sg:person.01244111736.76 schema:affiliation Ncae4ec1c7def4077b7fdc60fb2dd09f7
230 schema:familyName Ostrovski
231 schema:givenName Georg
232 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01244111736.76
233 rdf:type schema:Person
234 sg:person.01324724017.03 schema:affiliation Na92b5385b0a743e29d7b3e4b55fcdb4c
235 schema:familyName Mnih
236 schema:givenName Volodymyr
237 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01324724017.03
238 rdf:type schema:Person
239 sg:person.013266321653.49 schema:affiliation N9228fcfc3326476cb565e88b3d1f76b3
240 schema:familyName Fidjeland
241 schema:givenName Andreas K.
242 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013266321653.49
243 rdf:type schema:Person
244 sg:person.01354477236.72 schema:affiliation Ncca81628130249b0a41c243ed1fa7866
245 schema:familyName Kavukcuoglu
246 schema:givenName Koray
247 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01354477236.72
248 rdf:type schema:Person
249 sg:person.0604425216.82 schema:affiliation Ne026e61900b44ca7b87504182d03574b
250 schema:familyName Rusu
251 schema:givenName Andrei A.
252 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0604425216.82
253 rdf:type schema:Person
254 sg:person.0631073136.81 schema:affiliation N3a3aa7b536ed4f79858f6fcb870f8a8a
255 schema:familyName Silver
256 schema:givenName David
257 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0631073136.81
258 rdf:type schema:Person
259 sg:person.0703047436.03 schema:affiliation N095799d5c96e45bbbcbaeae476ab6de7
260 schema:familyName Antonoglou
261 schema:givenName Ioannis
262 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0703047436.03
263 rdf:type schema:Person
264 sg:person.0703136271.51 schema:affiliation N2dbd03c040b54110a2255ec3de4ef26c
265 schema:familyName Bellemare
266 schema:givenName Marc G.
267 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0703136271.51
268 rdf:type schema:Person
269 sg:person.0741767337.55 schema:affiliation N6caca14c13a444f390e77a6d2a8c256f
270 schema:familyName Hassabis
271 schema:givenName Demis
272 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0741767337.55
273 rdf:type schema:Person
274 sg:person.0745321536.28 schema:affiliation N52b6d9a1f12643aabb1cf31861e887d8
275 schema:familyName Veness
276 schema:givenName Joel
277 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0745321536.28
278 rdf:type schema:Person
279 sg:person.0751162636.50 schema:affiliation N905fa635a9f84456b5083b4c46b86020
280 schema:familyName King
281 schema:givenName Helen
282 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0751162636.50
283 rdf:type schema:Person
284 sg:pub.10.1007/11564096_32 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052945304
285 https://doi.org/10.1007/11564096_32
286 rdf:type schema:CreativeWork
287 sg:pub.10.1007/bf00344251 schema:sameAs https://app.dimensions.ai/details/publication/pub.1016635886
288 https://doi.org/10.1007/bf00344251
289 rdf:type schema:CreativeWork
290 sg:pub.10.1007/bf00993104 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026205858
291 https://doi.org/10.1007/bf00993104
292 rdf:type schema:CreativeWork
293 sg:pub.10.1007/s10514-009-9120-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018478429
294 https://doi.org/10.1007/s10514-009-9120-4
295 rdf:type schema:CreativeWork
296 sg:pub.10.1007/s11023-007-9079-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1044356842
297 https://doi.org/10.1007/s11023-007-9079-x
298 rdf:type schema:CreativeWork
299 sg:pub.10.1038/415318a schema:sameAs https://app.dimensions.ai/details/publication/pub.1022954489
300 https://doi.org/10.1038/415318a
301 rdf:type schema:CreativeWork
302 sg:pub.10.1038/nn.2304 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044077421
303 https://doi.org/10.1038/nn.2304
304 rdf:type schema:CreativeWork
305 sg:pub.10.1038/nn.3203 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030841884
306 https://doi.org/10.1038/nn.3203
307 rdf:type schema:CreativeWork
308 https://doi.org/10.1016/j.tins.2010.01.006 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000486991
309 rdf:type schema:CreativeWork
310 https://doi.org/10.1016/s0004-3702(98)00023-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1020908447
311 rdf:type schema:CreativeWork
312 https://doi.org/10.1037/0033-295x.102.3.419 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014544738
313 rdf:type schema:CreativeWork
314 https://doi.org/10.1109/5.726791 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061179979
315 rdf:type schema:CreativeWork
316 https://doi.org/10.1109/9.580874 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061245225
317 rdf:type schema:CreativeWork
318 https://doi.org/10.1109/cvpr.2005.254 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095271325
319 rdf:type schema:CreativeWork
320 https://doi.org/10.1109/iccv.2009.5459469 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093416695
321 rdf:type schema:CreativeWork
322 https://doi.org/10.1109/ijcnn.2010.5596468 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094389860
323 rdf:type schema:CreativeWork
324 https://doi.org/10.1109/tnn.1998.712192 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061716400
325 rdf:type schema:CreativeWork
326 https://doi.org/10.1113/jphysiol.1963.sp007079 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009974284
327 rdf:type schema:CreativeWork
328 https://doi.org/10.1126/science.1127647 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004607132
329 rdf:type schema:CreativeWork
330 https://doi.org/10.1126/science.275.5306.1593 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001523695
331 rdf:type schema:CreativeWork
332 https://doi.org/10.1145/1390156.1390187 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007561122
333 rdf:type schema:CreativeWork
334 https://doi.org/10.1145/203330.203343 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052366953
335 rdf:type schema:CreativeWork
336 https://doi.org/10.1561/2200000006 schema:sameAs https://app.dimensions.ai/details/publication/pub.1068001401
337 rdf:type schema:CreativeWork
338 https://doi.org/10.1613/jair.3912 schema:sameAs https://app.dimensions.ai/details/publication/pub.1105689878
339 rdf:type schema:CreativeWork
340 https://doi.org/10.2307/415721 schema:sameAs https://app.dimensions.ai/details/publication/pub.1070578988
341 rdf:type schema:CreativeWork
 




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


...