{"id":"https://openalex.org/W2914831223","doi":"https://doi.org/10.1007/978-3-030-31978-6_12","title":"Visual Rationalizations in Deep Reinforcement Learning for Atari Games","display_name":"Visual Rationalizations in Deep Reinforcement Learning for Atari Games","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2914831223","doi":"https://doi.org/10.1007/978-3-030-31978-6_12","mag":"2914831223"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-31978-6_12","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-31978-6_12","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://handle.uba.uva.nl/personal/pure/en/publications/visual-rationalizations-in-deep-reinforcement-learning-for-atari-games(cab1eca6-67b3-407f-88f5-f934b8116346).html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054006889","display_name":"Laurens Weitkamp","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Laurens Weitkamp","raw_affiliation_strings":["Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands","Informatics Institute, University of Amsterdam, Amsterdam; The Netherlands"],"affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"Informatics Institute, University of Amsterdam, Amsterdam; The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112286324","display_name":"Elise van der Pol","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Elise van der Pol","raw_affiliation_strings":["UvA-Bosch Delta Lab, University of Amsterdam, Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"UvA-Bosch Delta Lab, University of Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040372929","display_name":"Zeynep Akata","orcid":"https://orcid.org/0000-0002-1432-7747"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Zeynep Akata","raw_affiliation_strings":["UvA-Bosch Delta Lab, University of Amsterdam, Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"UvA-Bosch Delta Lab, University of Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054006889"],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":1.9314,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87972588,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8777652978897095},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6758170127868652},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6612164974212646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5891802310943604},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5519487261772156},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49913811683654785},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.49601611495018005},{"id":"https://openalex.org/keywords/decision-process","display_name":"Decision process","score":0.4872261583805084},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11085191369056702},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.1050553023815155},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08726271986961365},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.04805144667625427}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8777652978897095},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6758170127868652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6612164974212646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5891802310943604},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5519487261772156},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49913811683654785},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.49601611495018005},{"id":"https://openalex.org/C2984634286","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision process","level":2,"score":0.4872261583805084},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11085191369056702},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.1050553023815155},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08726271986961365},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.04805144667625427},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":9,"locations":[{"id":"doi:10.1007/978-3-030-31978-6_12","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-31978-6_12","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"},{"id":"pmh:oai:dare.uva.nl:openaire/cab1eca6-67b3-407f-88f5-f934b8116346","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/visual-rationalizations-in-deep-reinforcement-learning-for-atari-games(cab1eca6-67b3-407f-88f5-f934b8116346).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Weitkamp, L, van der Pol, E & Akata, Z 2018, Visual rationalizations in deep reinforcement learning for Atari games. in M Atzmueller & W Duivesteijn (eds), 30th Benelux Conference on Artificial Intelligence : BNAIC 2018 Preproceedings : November 8-9, 2018, Jheronimus Academy of Data Science (JADS), 's-Hertogenbosch, The Netherlands. BNAIC, vol. 30, 's-Hertogenbosch, pp. 315-329, 30th Benelux Conference on Artificial Intelligence, BNAIC 2018, s-Hertogenbosch, Netherlands, 8/11/18.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/1345450e-84b9-4088-8cdc-7416d85fa580","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/visual-rationalizations-in-deep-reinforcement-learning-for-atari-games(1345450e-84b9-4088-8cdc-7416d85fa580).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Weitkamp, L, van der Pol, E & Akata, Z 2019, Visual rationalizations in deep reinforcement learning for Atari games. in M Atzmueller & W Duivesteijn (eds), Artificial Intelligence : 30th Benelux Conference, BNAIC 2018, \u2018s-Hertogenbosch, The Netherlands, November 8\u20139, 2018 : revised selected papers. Communications in Computer and Information Science, vol. 1021, Cham, pp. 151-165, 30th Benelux Conference on Artificial Intelligence, BNAIC 2018, s-Hertogenbosch, Netherlands, 8/11/18. https://doi.org/10.1007/978-3-030-31978-6_12","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:1902.00566","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.00566","pdf_url":"https://arxiv.org/pdf/1902.00566","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/1345450e-84b9-4088-8cdc-7416d85fa580","is_oa":false,"landing_page_url":"https://hdl.handle.net/11245.1/1345450e-84b9-4088-8cdc-7416d85fa580","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Weitkamp , L , van der Pol , E & Akata , Z 2019 , Visual rationalizations in deep reinforcement learning for Atari games . in M Atzmueller & W Duivesteijn (eds) , Artificial Intelligence : 30th Benelux Conference, BNAIC 2018, \u2018s-Hertogenbosch, The Netherlands, November 8\u20139, 2018 : revised selected papers . Communications in Computer and Information Science , vol. 1021 , Cham , pp. 151-165 , 30th Benelux Conference on Artificial Intelligence, BNAIC 2018 , s-Hertogenbosch , Netherlands , 8/11/18 . https://doi.org/10.1007/978-3-030-31978-6_12","raw_type":"contributionToPeriodical"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/1345450e-84b9-4088-8cdc-7416d85fa580","is_oa":false,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/visual-rationalizations-in-deep-reinforcement-learning-for-atari-games(1345450e-84b9-4088-8cdc-7416d85fa580).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Artificial Intelligence: 30th Benelux Conference, BNAIC 2018, \u2018s-Hertogenbosch, The Netherlands, November 8\u20139, 2018 : revised selected papers, 151 - 165","raw_type":"info:eu-repo/semantics/conferencepaper"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/cab1eca6-67b3-407f-88f5-f934b8116346","is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/visual-rationalizations-in-deep-reinforcement-learning-for-atari-games(cab1eca6-67b3-407f-88f5-f934b8116346).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"30th Benelux Conference on Artificial Intelligence: BNAIC 2018 Preproceedings : November 8-9, 2018, Jheronimus Academy of Data Science (JADS), 's-Hertogenbosch, The Netherlands, 315 - 329","raw_type":"info:eu-repo/semantics/conferencepaper"},{"id":"doi:10.48550/arxiv.1902.00566","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1902.00566","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:2914831223","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:dare.uva.nl:openaire/cab1eca6-67b3-407f-88f5-f934b8116346","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/visual-rationalizations-in-deep-reinforcement-learning-for-atari-games(cab1eca6-67b3-407f-88f5-f934b8116346).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Weitkamp, L, van der Pol, E & Akata, Z 2018, Visual rationalizations in deep reinforcement learning for Atari games. in M Atzmueller & W Duivesteijn (eds), 30th Benelux Conference on Artificial Intelligence : BNAIC 2018 Preproceedings : November 8-9, 2018, Jheronimus Academy of Data Science (JADS), 's-Hertogenbosch, The Netherlands. BNAIC, vol. 30, 's-Hertogenbosch, pp. 315-329, 30th Benelux Conference on Artificial Intelligence, BNAIC 2018, s-Hertogenbosch, Netherlands, 8/11/18.","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W1921523184","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2257979135","https://openalex.org/W2260756217","https://openalex.org/W2332488709","https://openalex.org/W2592915494","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2754517384","https://openalex.org/W2761873684","https://openalex.org/W2949608212","https://openalex.org/W2962680264","https://openalex.org/W2962858109","https://openalex.org/W2962938178","https://openalex.org/W2962954781","https://openalex.org/W2963609017","https://openalex.org/W2964043796","https://openalex.org/W2964118342","https://openalex.org/W3103780890","https://openalex.org/W4230563027","https://openalex.org/W4240752140","https://openalex.org/W6601104142","https://openalex.org/W6607167723","https://openalex.org/W6633651462","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W2978184346","https://openalex.org/W2145339207","https://openalex.org/W2996274873","https://openalex.org/W2998825830","https://openalex.org/W3103780890","https://openalex.org/W2962851944","https://openalex.org/W2964014957","https://openalex.org/W3096684011","https://openalex.org/W3214243223","https://openalex.org/W2920768993","https://openalex.org/W2854769010","https://openalex.org/W3033065426","https://openalex.org/W3129949865","https://openalex.org/W3037198355","https://openalex.org/W2097113539","https://openalex.org/W2585047082","https://openalex.org/W3128190331","https://openalex.org/W1607218107","https://openalex.org/W2949969799","https://openalex.org/W2972522277"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}