{"id":"https://openalex.org/W4385767684","doi":"https://doi.org/10.24963/ijcai.2023/477","title":"DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards","display_name":"DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767684","doi":"https://doi.org/10.24963/ijcai.2023/477"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/477","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/477","pdf_url":"https://www.ijcai.org/proceedings/2023/0477.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0477.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015877402","display_name":"Shanchuan Wan","orcid":"https://orcid.org/0000-0002-3771-1522"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shanchuan Wan","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669162","display_name":"Yujin Tang","orcid":"https://orcid.org/0000-0002-8641-1219"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113520","display_name":"Brain (Germany)","ror":"https://ror.org/01gamcy45","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210113520"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Yujin Tang","raw_affiliation_strings":["Google Research, Brain Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Brain Team","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113520"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040295235","display_name":"Yingtao Tian","orcid":"https://orcid.org/0000-0002-3602-259X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113520","display_name":"Brain (Germany)","ror":"https://ror.org/01gamcy45","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210113520"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Yingtao Tian","raw_affiliation_strings":["Google Research, Brain Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Brain Team","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113520"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103172324","display_name":"Tomoyuki Kaneko","orcid":"https://orcid.org/0000-0001-8051-2388"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoyuki Kaneko","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3263,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64692836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4289","last_page":"4298"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9980000257492065,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.8934010863304138},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.740937352180481},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7205328941345215},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7092079520225525},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.579376220703125},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5542640686035156},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4936424493789673},{"id":"https://openalex.org/keywords/intrinsic-motivation","display_name":"Intrinsic motivation","score":0.4891274571418762},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16313624382019043},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12055990099906921}],"concepts":[{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.8934010863304138},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.740937352180481},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7205328941345215},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7092079520225525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.579376220703125},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5542640686035156},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4936424493789673},{"id":"https://openalex.org/C2985564149","wikidata":"https://www.wikidata.org/wiki/Q644302","display_name":"Intrinsic motivation","level":2,"score":0.4891274571418762},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16313624382019043},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12055990099906921},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/477","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/477","pdf_url":"https://www.ijcai.org/proceedings/2023/0477.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/477","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/477","pdf_url":"https://www.ijcai.org/proceedings/2023/0477.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767684.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1511694993","https://openalex.org/W2040870580","https://openalex.org/W2112796928","https://openalex.org/W2145339207","https://openalex.org/W2158125716","https://openalex.org/W2436711315","https://openalex.org/W2596982695","https://openalex.org/W2736601468","https://openalex.org/W2766736793","https://openalex.org/W2949475445","https://openalex.org/W2953722837","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2964067469","https://openalex.org/W2964199361","https://openalex.org/W2973525135","https://openalex.org/W2994073215","https://openalex.org/W2995298643","https://openalex.org/W3084269620","https://openalex.org/W3115293622","https://openalex.org/W3129170303","https://openalex.org/W3211731195","https://openalex.org/W3216772467","https://openalex.org/W4287867830","https://openalex.org/W4293411878","https://openalex.org/W4294107275","https://openalex.org/W4297732320","https://openalex.org/W4297797010","https://openalex.org/W4301785137"],"related_works":["https://openalex.org/W2381242807","https://openalex.org/W3126131230","https://openalex.org/W2347541121","https://openalex.org/W2080951048","https://openalex.org/W4288804799","https://openalex.org/W3032237421","https://openalex.org/W2390346111","https://openalex.org/W2965546495","https://openalex.org/W3011883280","https://openalex.org/W2369082698"],"abstract_inverted_index":{"Exploration":[0],"is":[1,12,47],"a":[2,13,48,82,94,115,135],"fundamental":[3],"aspect":[4],"of":[5,19,34,53,154],"reinforcement":[6],"learning":[7],"(RL),":[8],"and":[9,56,66,109,124,150],"its":[10],"effectiveness":[11,33],"deciding":[14],"factor":[15],"in":[16,43,63,85,128],"the":[17,32,51,61,64,67,72,103,112,139,147,151],"performance":[18],"RL":[20],"algorithms,":[21],"especially":[22],"when":[23],"facing":[24],"sparse":[25],"extrinsic":[26],"rewards.":[27],"Recent":[28],"studies":[29],"have":[30],"shown":[31],"encouraging":[35],"exploration":[36,126],"with":[37,93,102,114],"intrinsic":[38,91,156],"rewards":[39],"estimated":[40],"from":[41],"novelties":[42],"observations.":[44],"However,":[45],"there":[46],"gap":[49],"between":[50],"novelty":[52,104],"an":[54,57,90],"observation":[55],"exploration,":[58],"as":[59],"both":[60,122,146],"stochasticity":[62],"environment":[65],"agent's":[68],"behavior":[69],"may":[70],"affect":[71],"observation.":[73],"To":[74],"evaluate":[75],"exploratory":[76],"behaviors":[77],"accurately,":[78],"we":[79,87],"propose":[80],"DEIR,":[81],"novel":[83],"method":[84],"which":[86],"theoretically":[88],"derive":[89],"reward":[92,113],"conditional":[95],"mutual":[96],"information":[97],"term":[98],"that":[99,131],"principally":[100],"scales":[101],"contributed":[105],"by":[106],"agent":[107],"explorations,":[108],"then":[110],"implement":[111],"discriminative":[116],"forward":[117],"model.":[118],"Extensive":[119],"experiments":[120],"on":[121,143],"standard":[123],"advanced":[125],"tasks":[127],"MiniGrid":[129],"show":[130],"DEIR":[132],"quickly":[133],"learns":[134],"better":[136],"policy":[137],"than":[138],"baselines.":[140],"Our":[141],"evaluations":[142],"ProcGen":[144],"demonstrate":[145],"generalization":[148],"capability":[149],"general":[152],"applicability":[153],"our":[155],"reward.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}