{"id":"https://openalex.org/W4414360278","doi":"https://doi.org/10.24963/ijcai.2025/723","title":"BILE: An Effective Behavior-based Latent Exploration Scheme for Deep Reinforcement Learning","display_name":"BILE: An Effective Behavior-based Latent Exploration Scheme for Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360278","doi":"https://doi.org/10.24963/ijcai.2025/723"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/723","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100377920","display_name":"Yiming Wang","orcid":"https://orcid.org/0000-0001-7330-2235"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Yiming Wang","raw_affiliation_strings":["University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kaiyan Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN","MO"],"is_corresponding":false,"raw_author_name":"Kaiyan Zhao","raw_affiliation_strings":["University of Macau","Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau","institution_ids":["https://openalex.org/I204512498"]},{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041907871","display_name":"Yan Li","orcid":"https://orcid.org/0000-0002-6306-0436"},"institutions":[{"id":"https://openalex.org/I182722699","display_name":"Shenzhen Polytechnic University","ror":"https://ror.org/00d2w9g53","country_code":"CN","type":"education","lineage":["https://openalex.org/I182722699"]},{"id":"https://openalex.org/I4210120584","display_name":"The Polytechnic University of Japan","ror":"https://ror.org/02f0psx94","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210120584"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Yan Li","raw_affiliation_strings":["Shenzhen Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Polytechnic University","institution_ids":["https://openalex.org/I182722699","https://openalex.org/I4210120584"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035706700","display_name":"Leong Hou U","orcid":"https://orcid.org/0000-0002-5135-5165"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Leong Hou U","raw_affiliation_strings":["University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6497","last_page":"6505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9702000021934509,"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":0.9702000021934509,"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":0.7692999839782715},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7197999954223633},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5476999878883362},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4867999851703644},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4542999863624573},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.41019999980926514},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4052000045776367},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.38760000467300415}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7692999839782715},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7197999954223633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6527000069618225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6452999711036682},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5404999852180481},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4542999863624573},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4052000045776367},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C104060986","wikidata":"https://www.wikidata.org/wiki/Q180046","display_name":"Space exploration","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/723","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Efficient":[0],"exploration":[1,19,23,86,112],"of":[2,10,25,113,129,162],"state":[3,47,115,131],"spaces":[4],"is":[5,63],"critical":[6],"for":[7,124],"the":[8,70,93,114,130,158],"success":[9],"deep":[11],"reinforcement":[12],"learning":[13,38],"(RL).":[14],"While":[15],"many":[16],"methods":[17],"leverage":[18],"bonuses":[20],"to":[21,64,84,95,109],"encourage":[22,85],"instead":[24],"relying":[26],"solely":[27],"on":[28,139],"extrinsic":[29],"rewards,":[30],"these":[31,51],"bonus-based":[32],"approaches":[33],"often":[34],"face":[35],"challenges":[36],"with":[37,45,98],"efficiency":[39],"and":[40,102,126,152,160],"scalability,":[41],"especially":[42],"in":[43,87,146,150],"environments":[44],"high-dimensional":[46,140],"spaces.":[48],"To":[49],"address":[50],"issues,":[52],"we":[53,118],"propose":[54],"BehavIoral":[55],"metric-based":[56],"Latent":[57],"Exploration":[58],"(BILE).":[59],"The":[60],"core":[61],"idea":[62],"learn":[65],"a":[66,120],"compact":[67],"representation":[68],"within":[69],"behavioral":[71,122],"metric":[72,123],"space":[73],"that":[74],"preserves":[75],"value":[76,100],"differences":[77],"between":[78],"states.":[79],"By":[80],"introducing":[81],"additional":[82],"rewards":[83],"this":[88],"latent":[89],"space,":[90],"BILE":[91],"drives":[92],"agent":[94],"visit":[96],"states":[97],"higher":[99],"diversity":[101],"exhibit":[103],"more":[104,110],"behaviorally":[105],"distinct":[106],"actions,":[107],"leading":[108],"effective":[111],"space.":[116],"Additionally,":[117],"present":[119],"novel":[121],"efficient":[125],"robust":[127],"training":[128],"encoder,":[132],"backed":[133],"by":[134],"theoretical":[135],"guarantees.":[136],"Extensive":[137],"experiments":[138],"environments,":[141],"including":[142],"realistic":[143],"indoor":[144],"scenarios":[145],"Habitat,":[147],"robotic":[148],"tasks":[149],"Robosuite,":[151],"challenging":[153],"discrete":[154],"Minigrid":[155],"benchmarks,":[156],"demonstrate":[157],"superiority":[159],"scalability":[161],"our":[163],"method":[164],"over":[165],"other":[166],"approaches.":[167]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}