{"id":"https://openalex.org/W4415708548","doi":"https://doi.org/10.1109/icme59968.2025.11210033","title":"Multimodal Causal Reasoning-Guided Intrinsic Goals for Efficient Task Completion in Reinforcement Learning","display_name":"Multimodal Causal Reasoning-Guided Intrinsic Goals for Efficient Task Completion in Reinforcement Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708548","doi":"https://doi.org/10.1109/icme59968.2025.11210033"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5102002765","display_name":"Tong Wu","orcid":"https://orcid.org/0009-0003-0654-8245"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Wu","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Software Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Software Engineering,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044904587","display_name":"Yi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Wen","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Software Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Software Engineering,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101878135","display_name":"Guangchun Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangchun Luo","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Software Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Software Engineering,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047014422","display_name":"Lingfu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingfu Wang","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Software Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Software Engineering,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011468623","display_name":"Qiuran Li","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuran Li","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Computer Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102138879","display_name":"Dayong Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dayong Zhu","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Software Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Software Engineering,China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27844643,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.796500027179718,"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":0.796500027179718,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.025699999183416367,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.012299999594688416,"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/leverage","display_name":"Leverage (statistics)","score":0.7601000070571899},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6790000200271606},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6146000027656555},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.5284000039100647},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.41760000586509705},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.39489999413490295},{"id":"https://openalex.org/keywords/causal-reasoning","display_name":"Causal reasoning","score":0.3650999963283539}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7601000070571899},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6790000200271606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6424999833106995},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6146000027656555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5630000233650208},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.5284000039100647},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43160000443458557},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.41760000586509705},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.3650999963283539},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29580000042915344},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2903999984264374},{"id":"https://openalex.org/C2985564149","wikidata":"https://www.wikidata.org/wiki/Q644302","display_name":"Intrinsic motivation","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337495","display_name":"Technology Development","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2145688713","https://openalex.org/W2963523627","https://openalex.org/W3133932964","https://openalex.org/W3217360279","https://openalex.org/W4382239281"],"related_works":[],"abstract_inverted_index":{"Exploration":[0],"in":[1,9,29,90,127],"sparse":[2],"reward":[3],"environments":[4,31,130],"is":[5],"a":[6,72,94],"long-standing":[7],"challenge":[8],"reinforcement":[10],"learning.":[11],"While":[12],"advanced":[13],"methods":[14],"often":[15],"enhance":[16],"exploration":[17,155],"by":[18],"introducing":[19],"intrinsic":[20,44,75,101],"rewards,":[21],"they":[22],"may":[23,39],"lead":[24],"agents":[25,38,113],"to":[26,50,61,67,85,97,114,143],"local":[27],"optima":[28],"procedurally-generated":[30],"with":[32,103],"high":[33],"uncertainty":[34],"and":[35,70,99,116,153],"diversity.":[36],"Specifically,":[37],"over":[40],"rely":[41],"on":[42,108],"certain":[43],"signals,":[45],"neglecting":[46],"long-term":[47],"tasks":[48,69],"tied":[49],"external":[51,68],"rewards.":[52],"To":[53],"address":[54],"this,":[55],"we":[56],"leverage":[57,140],"multimodal":[58,83],"causal":[59,64,88,106,141],"reasoning":[60],"identify":[62],"key":[63],"variables":[65],"relevant":[66],"propose":[71],"Causal":[73],"Reasoning-guided":[74],"Goal":[76],"generation":[77],"method":[78,126],"(CRG).":[79],"Our":[80],"approach":[81],"integrates":[82],"data":[84],"abstract":[86],"invariant":[87],"relationships":[89,142],"dynamic":[91],"environments,":[92],"using":[93],"teacher":[95],"network":[96],"evaluate":[98],"select":[100],"goals":[102],"the":[104],"strongest":[105],"impact":[107],"task":[109,121,151],"completion.":[110],"This":[111],"enables":[112],"explore":[115],"learn":[117],"efficiently,":[118],"enhancing":[119],"overall":[120],"performance.":[122],"We":[123],"evaluated":[124],"our":[125],"several":[128],"MiniGrid":[129],"of":[131],"varying":[132],"complexity.":[133],"Experimental":[134],"results":[135],"show":[136],"that":[137],"CRG":[138],"can":[139],"generate":[144],"more":[145],"effective":[146],"internal":[147],"goals,":[148],"significantly":[149],"accelerating":[150],"completion":[152],"improving":[154],"efficiency.":[156]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-30T00:00:00"}