{"id":"https://openalex.org/W3208966735","doi":"https://doi.org/10.1145/3459637.3482326","title":"CIExplore","display_name":"CIExplore","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3208966735","doi":"https://doi.org/10.1145/3459637.3482326","mag":"3208966735"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482326","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012369858","display_name":"Huanhuan Yang","orcid":"https://orcid.org/0000-0002-9632-2543"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanhuan Yang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019758816","display_name":"Dianxi Shi","orcid":"https://orcid.org/0000-0002-8112-371X"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dianxi Shi","raw_affiliation_strings":["Defense Innovation Institute & Tianjin Artificial Intelligence Innovation Center, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Defense Innovation Institute & Tianjin Artificial Intelligence Innovation Center, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016270698","display_name":"Chenran Zhao","orcid":"https://orcid.org/0009-0008-6261-9585"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenran Zhao","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047563276","display_name":"Guojun Xie","orcid":"https://orcid.org/0000-0002-3787-2983"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guojun Xie","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075939329","display_name":"Shaowu Yang","orcid":"https://orcid.org/0000-0002-8398-5612"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaowu Yang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2799,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65140127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2321","last_page":"2330"},"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/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9776999950408936,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.8815464973449707},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7074185013771057},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7036463022232056},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.6033668518066406},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5364113450050354},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.516946017742157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49018269777297974},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4631689488887787},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3755861520767212},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2016994059085846},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13081204891204834},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.12704816460609436}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.8815464973449707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7074185013771057},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7036463022232056},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.6033668518066406},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5364113450050354},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.516946017742157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49018269777297974},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4631689488887787},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3755861520767212},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2016994059085846},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13081204891204834},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12704816460609436},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3459637.3482326","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G1860839707","display_name":null,"funder_award_id":"2017YFB1001901","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1980358463","https://openalex.org/W1988526405","https://openalex.org/W2096563449","https://openalex.org/W2101524054","https://openalex.org/W2145339207","https://openalex.org/W2617547828","https://openalex.org/W2752448298","https://openalex.org/W2793963910","https://openalex.org/W2913668833","https://openalex.org/W2963523627","https://openalex.org/W2981038142","https://openalex.org/W2997289589","https://openalex.org/W3100366369","https://openalex.org/W3123212791","https://openalex.org/W4249440929"],"related_works":["https://openalex.org/W3201448254","https://openalex.org/W4286970243","https://openalex.org/W2065956941","https://openalex.org/W4285676344","https://openalex.org/W3094054656","https://openalex.org/W2066431708","https://openalex.org/W2123270665","https://openalex.org/W2064460959","https://openalex.org/W2060310955","https://openalex.org/W4382584175"],"abstract_inverted_index":{"Learning":[0],"in":[1,9,42,53,70,187],"a":[2,6,84,101],"sparse-reward":[3],"setting":[4],"is":[5,100,112,162,196],"well-known":[7],"challenge":[8,18],"RL":[10],"(Reinforcement":[11],"Learning).":[12],"In":[13],"the":[14,75,97,113,136,142,145,158,183,188],"single-agent":[15],"domain,":[16],"this":[17,71,176],"can":[19],"be":[20,206],"addressed":[21],"by":[22,27,164],"introducing":[23],"exploration":[24],"bonuses":[25],"driven":[26],"intrinsic":[28,88,98,177],"motivation":[29],"to":[30,33,134,174,208],"encourage":[31],"agents":[32,131],"visit":[34],"unseen":[35],"states.":[36],"However,":[37],"naively":[38],"applying":[39],"these":[40],"methods":[41],"MARL":[43,203],"(Multi-Agent":[44],"Reinforcement":[45],"Learning)":[46],"cooperative":[47],"settings":[48,210],"with":[49,198],"sparse":[50],"rewards":[51],"results":[52],"some":[54],"inevitable":[55],"problems:":[56],"misunderstanding":[57],"environmental":[58],"knowledge":[59],"and":[60,77,90,107,127,192,201,205],"lack":[61],"of":[62,87,103,115,120,129,147,185],"collaboration":[63],"among":[64],"agents,":[65,166],"etc.":[66],"Based":[67],"on":[68,151],"this,":[69],"paper,":[72],"we":[73,167],"propose":[74],"Curiosity":[76],"Influence-based":[78],"Explore":[79],"(CIExplore)":[80],"method,":[81],"which":[82],"includes":[83],"new":[85],"form":[86],"reward":[89,99,106,161,178],"an":[91,118,169],"internal":[92,170],"counterfactual":[93,171],"advantage":[94,172],"function.":[95],"Concretely,":[96],"combination":[102],"joint":[104,125,139,159],"curiosity":[105,160],"influence":[108,146],"reward.":[109],"The":[110],"former":[111],"variance":[114],"outputs":[116],"across":[117],"ensemble":[119],"prediction":[121],"models":[122],"that":[123,157,194],"take":[124],"observations":[126],"actions":[128],"all":[130,165],"as":[132],"inputs":[133],"predict":[135],"next":[137],"time's":[138],"observations.":[140],"And":[141],"latter":[143],"quantifies":[144],"one":[148],"agent's":[149],"behavior":[150],"other":[152],"agents'":[153,212],"state-value":[154],"functions.":[155],"Given":[156],"shared":[163],"compute":[168],"function":[173],"address":[175],"assignment":[179],"problem.":[180],"We":[181],"demonstrate":[182],"efficacy":[184],"CIExplore":[186],"multi-agent":[189],"grid-world":[190],"environments":[191],"show":[193],"it":[195],"compatible":[197],"both":[199],"on-policy":[200],"off-policy":[202],"algorithms":[204],"scalable":[207],"complex":[209],"where":[211],"number":[213],"or":[214],"environment":[215],"randomness":[216],"increases.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2021-11-08T00:00:00"}