{"id":"https://openalex.org/W4415539754","doi":"https://doi.org/10.1145/3746027.3755206","title":"Multimodal Dual Population Evolutionary Reinforcement Learning","display_name":"Multimodal Dual Population Evolutionary Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539754","doi":"https://doi.org/10.1145/3746027.3755206"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755206","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5107910721","display_name":"Yao Zhang","orcid":"https://orcid.org/0009-0000-6993-3501"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhang","raw_affiliation_strings":["Harbin Engineering University, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0000-6993-3501","affiliations":[{"raw_affiliation_string":"Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101843988","display_name":"Ping Huang","orcid":"https://orcid.org/0000-0002-4170-8916"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Huang","raw_affiliation_strings":["Harbin Engineering University, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-4170-8916","affiliations":[{"raw_affiliation_string":"Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107940793","display_name":"Rui Zhang","orcid":"https://orcid.org/0009-0006-6793-8310"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["Harbin Engineering University, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0006-6793-8310","affiliations":[{"raw_affiliation_string":"Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151727225"],"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":"1490","last_page":"1499"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9970999956130981,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9908000230789185,"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":0.8321999907493591},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.6078000068664551},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5565000176429749},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5552999973297119},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5304999947547913},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.5105000138282776},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44699999690055847}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8321999907493591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6901000142097473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6492000222206116},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.6078000068664551},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5565000176429749},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5552999973297119},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5304999947547913},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.5105000138282776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4602000117301941},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.43299999833106995},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4259999990463257},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C199505168","wikidata":"https://www.wikidata.org/wiki/Q3267529","display_name":"Evolutionary robotics","level":3,"score":0.3172000050544739},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C207002847","wikidata":"https://www.wikidata.org/wiki/Q2912857","display_name":"Evolution strategy","level":3,"score":0.26829999685287476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755206","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2099746672","https://openalex.org/W2132083787","https://openalex.org/W2158782408","https://openalex.org/W2662297521","https://openalex.org/W2951278471","https://openalex.org/W2962687375","https://openalex.org/W2967727187","https://openalex.org/W3100789280","https://openalex.org/W3163251780","https://openalex.org/W3187600255","https://openalex.org/W3197886029","https://openalex.org/W4220747123","https://openalex.org/W4287757595","https://openalex.org/W4308177782","https://openalex.org/W4315574835","https://openalex.org/W4366680618","https://openalex.org/W4377695283","https://openalex.org/W4385566404","https://openalex.org/W4387369436","https://openalex.org/W4392190020","https://openalex.org/W4401179578"],"related_works":[],"abstract_inverted_index":{"The":[0,179],"integration":[1],"of":[2,61,72,167,184],"Evolutionary":[3,84],"Algorithms":[4],"(EAs)":[5],"and":[6,25,58,70,95,152,171,201],"Reinforcement":[7,85],"Learning":[8,86],"(RL)":[9],"offers":[10],"a":[11,101,124,135,182,195,202],"new":[12],"paradigm":[13],"for":[14,130],"complex":[15],"decision-making":[16],"tasks,":[17],"especially":[18],"through":[19,91],"methods":[20,42],"that":[21,188],"optimize":[22,140],"actor":[23,147],"populations":[24,170],"critics":[26],"collaboratively":[27],"(e.g.,":[28],"DBCEM-TD3,":[29],"QD-RL),":[30],"collectively":[31],"referred":[32],"to":[33,52,65,139,144,162],"as":[34],"the":[35,55,59,62,68,73,118,131,141,146,157,164,168,173,192],"Actor-Population":[36],"Critic":[37],"(APC)":[38],"framework.":[39],"However,":[40],"existing":[41],"still":[43],"face":[44],"two":[45],"major":[46],"challenges:":[47],"traditional":[48],"feature":[49,93],"inputs":[50],"fail":[51],"fully":[53],"capture":[54],"spatial":[56,115],"relationships,":[57],"design":[60,156],"critic":[63,125],"struggles":[64],"balance":[66],"both":[67],"quality":[69,151],"diversity":[71],"policies.":[74],"To":[75],"address":[76],"these":[77],"issues,":[78],"we":[79,155],"propose":[80],"Multimodal":[81],"Dual":[82],"Population":[83],"(M-DPERL),":[87],"which":[88,109],"achieves":[89],"breakthroughs":[90],"cross-modal":[92],"augmentation":[94],"dual-population":[96],"coevolution.":[97,178],"On":[98,117],"one":[99],"hand,":[100,120],"feature-image":[102],"bimodal":[103],"input":[104],"enhancement":[105],"mechanism":[106,161],"is":[107],"proposed,":[108],"dynamically":[110],"encodes":[111],"environmental":[112],"features":[113],"into":[114,127],"heatmaps.":[116],"other":[119],"this":[121],"method":[122],"introduces":[123],"population":[126,148],"APC":[128],"and,":[129],"first":[132],"time,":[133],"proposes":[134],"population-guided":[136],"fitness":[137],"metric":[138],"critic's":[142],"ability":[143],"guide":[145],"in":[149,176,198,205],"balancing":[150],"diversity.":[153],"Additionally,":[154],"Flow-Fix":[158],"Dynamics":[159],"(FFD)":[160],"regulate":[163],"update":[165],"rhythm":[166],"dual":[169],"alleviate":[172],"evolutionary":[174],"chaos":[175],"their":[177],"results":[180],"across":[181],"series":[183],"MUJOCO":[185],"tasks":[186],"demonstrate":[187],"M-DPERL":[189],"significantly":[190],"outperforms":[191],"baselines,":[193],"with":[194],"19.2%":[196],"improvement":[197],"sample":[199],"efficiency":[200],"17.1%":[203],"increase":[204],"final":[206],"performance.":[207]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}