{"id":"https://openalex.org/W3041394538","doi":"https://doi.org/10.24963/ijcai.2020/733","title":"Towards High-Level Intrinsic Exploration in Reinforcement Learning","display_name":"Towards High-Level Intrinsic Exploration in Reinforcement Learning","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3041394538","doi":"https://doi.org/10.24963/ijcai.2020/733","mag":"3041394538"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/733","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/733","pdf_url":"https://www.ijcai.org/proceedings/2020/0733.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0733.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069965217","display_name":"Nicolas Bougie","orcid":"https://orcid.org/0000-0001-9856-0038"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nicolas Bougie","raw_affiliation_strings":["National Institute of Informatics","The Graduate University for Advanced Studies, Sokendai","National Institute of Informatics, Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"The Graduate University for Advanced Studies, Sokendai","institution_ids":["https://openalex.org/I200475212"]},{"raw_affiliation_string":"National Institute of Informatics, Tokyo","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081854769","display_name":"Ryutaro Ichise","orcid":"https://orcid.org/0000-0001-8474-0150"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryutaro Ichise","raw_affiliation_strings":["National Institute of informatics","The Graduate University for Advanced Studies, Sokendai","National Institute of Informatics, Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of informatics","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"The Graduate University for Advanced Studies, Sokendai","institution_ids":["https://openalex.org/I200475212"]},{"raw_affiliation_string":"National Institute of Informatics, Tokyo","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.46,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.64115911,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5186","last_page":"5187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9835000038146973,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.975600004196167,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/curiosity","display_name":"Curiosity","score":0.9476439952850342},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8702594041824341},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7005335688591003},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45541927218437195},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41825899481773376},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3281237483024597},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13958638906478882},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.11952477693557739},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07776102423667908}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.9476439952850342},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8702594041824341},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7005335688591003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45541927218437195},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41825899481773376},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3281237483024597},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13958638906478882},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11952477693557739},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07776102423667908}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/733","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/733","pdf_url":"https://www.ijcai.org/proceedings/2020/0733.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/733","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/733","pdf_url":"https://www.ijcai.org/proceedings/2020/0733.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3041394538.pdf","grobid_xml":"https://content.openalex.org/works/W3041394538.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2417786368","https://openalex.org/W2614839826","https://openalex.org/W2895453875","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2963864421","https://openalex.org/W2964067469","https://openalex.org/W4298857966"],"related_works":["https://openalex.org/W3094054656","https://openalex.org/W4285676344","https://openalex.org/W2123270665","https://openalex.org/W4382584175","https://openalex.org/W2060310955","https://openalex.org/W2284924956","https://openalex.org/W3043413210","https://openalex.org/W2613740288","https://openalex.org/W4252460700","https://openalex.org/W4401386752"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,76],"learning":[2],"(DRL)":[3],"methods":[4,37],"traditionally":[5],"struggle":[6],"with":[7,89],"tasks":[8],"where":[9],"environment":[10],"rewards":[11],"are":[12],"sparse":[13],"or":[14],"delayed,":[15],"which":[16],"entails":[17],"that":[18,71,87,96,122],"exploration":[19,42,54,74,91,100,125],"remains":[20],"one":[21],"of":[22,26,29,48,60],"the":[23,58,106,114],"key":[24],"challenges":[25],"DRL.":[27],"Instead":[28],"solely":[30],"relying":[31],"on":[32],"extrinsic":[33],"rewards,":[34],"many":[35],"state-of-the-art":[36],"use":[38],"intrinsic":[39,68],"curiosity":[40,79,104],"as":[41,105],"signal.":[43],"While":[44],"they":[45],"hold":[46],"promise":[47],"better":[49],"local":[50,90],"exploration,":[51],"discovering":[52],"global":[53],"strategies":[55],"is":[56,81],"beyond":[57],"reach":[59],"current":[61],"methods.":[62],"We":[63,102],"propose":[64],"a":[65,84,93],"novel":[66],"end-to-end":[67],"reward":[69,86,95],"formulation":[70],"introduces":[72],"high-level":[73,124],"in":[75,108,133],"learning.":[77],"Our":[78],"signal":[80],"driven":[82],"by":[83],"fast":[85],"deals":[88],"and":[92],"slow":[94],"incentivizes":[97],"long-time":[98],"horizon":[99],"strategies.":[101],"formulate":[103],"error":[107],"an":[109],"agent\u2019s":[110],"ability":[111],"to":[112,129],"reconstruct":[113],"observations":[115],"given":[116],"their":[117],"contexts.":[118],"Experimental":[119],"results":[120],"show":[121],"this":[123],"enables":[126],"our":[127],"agents":[128],"outperform":[130],"prior":[131],"work":[132],"several":[134],"Atari":[135],"games.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}