{"id":"https://openalex.org/W4389315154","doi":"https://doi.org/10.1109/cog57401.2023.10333236","title":"Enabling Multi-Agent Transfer Reinforcement Learning via Scenario Independent Representation","display_name":"Enabling Multi-Agent Transfer Reinforcement Learning via Scenario Independent Representation","publication_year":2023,"publication_date":"2023-08-21","ids":{"openalex":"https://openalex.org/W4389315154","doi":"https://doi.org/10.1109/cog57401.2023.10333236"},"language":"en","primary_location":{"id":"doi:10.1109/cog57401.2023.10333236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog57401.2023.10333236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.08184","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031503895","display_name":"Ayesha Siddika Nipu","orcid":null},"institutions":[{"id":"https://openalex.org/I119942284","display_name":"Missouri State University","ror":"https://ror.org/01d2sez20","country_code":"US","type":"education","lineage":["https://openalex.org/I119942284"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayesha Siddika Nipu","raw_affiliation_strings":["Missouri State University,Department of Computer Science,Springfield,U.S","Department of Computer Science, Missouri State University, Springfield, U.S"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Missouri State University,Department of Computer Science,Springfield,U.S","institution_ids":["https://openalex.org/I119942284"]},{"raw_affiliation_string":"Department of Computer Science, Missouri State University, Springfield, U.S","institution_ids":["https://openalex.org/I119942284"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001784302","display_name":"Siming Liu","orcid":"https://orcid.org/0000-0001-9004-1380"},"institutions":[{"id":"https://openalex.org/I119942284","display_name":"Missouri State University","ror":"https://ror.org/01d2sez20","country_code":"US","type":"education","lineage":["https://openalex.org/I119942284"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siming Liu","raw_affiliation_strings":["Missouri State University,Department of Computer Science,Springfield,U.S","Department of Computer Science, Missouri State University, Springfield, U.S"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Missouri State University,Department of Computer Science,Springfield,U.S","institution_ids":["https://openalex.org/I119942284"]},{"raw_affiliation_string":"Department of Computer Science, Missouri State University, Springfield, U.S","institution_ids":["https://openalex.org/I119942284"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048506833","display_name":"Anthony M. Harris","orcid":"https://orcid.org/0000-0002-9451-2095"},"institutions":[{"id":"https://openalex.org/I119942284","display_name":"Missouri State University","ror":"https://ror.org/01d2sez20","country_code":"US","type":"education","lineage":["https://openalex.org/I119942284"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony Harris","raw_affiliation_strings":["Missouri State University,Department of Computer Science,Springfield,U.S","Department of Computer Science, Missouri State University, Springfield, U.S"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Missouri State University,Department of Computer Science,Springfield,U.S","institution_ids":["https://openalex.org/I119942284"]},{"raw_affiliation_string":"Department of Computer Science, Missouri State University, Springfield, U.S","institution_ids":["https://openalex.org/I119942284"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I119942284"],"apc_list":null,"apc_paid":null,"fwci":0.9592,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79846482,"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9944000244140625,"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":0.9799000024795532,"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":0.8135063648223877},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7991423010826111},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6674830317497253},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5963998436927795},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.498532772064209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4936271905899048},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.4331914782524109},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.41730719804763794},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.4129878580570221},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3589709997177124},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34978583455085754},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.1826060712337494},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09567734599113464}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8135063648223877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7991423010826111},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6674830317497253},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5963998436927795},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.498532772064209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4936271905899048},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.4331914782524109},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.41730719804763794},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4129878580570221},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3589709997177124},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34978583455085754},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.1826060712337494},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09567734599113464},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cog57401.2023.10333236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog57401.2023.10333236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2402.08184","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.08184","pdf_url":"https://arxiv.org/pdf/2402.08184","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:bearworks.missouristate.edu:articles00-1633","is_oa":false,"landing_page_url":"https://bearworks.missouristate.edu/articles00/634","pdf_url":null,"source":{"id":"https://openalex.org/S4377196450","display_name":"BearWorks (Missouri State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119942284","host_organization_name":"Missouri State University","host_organization_lineage":["https://openalex.org/I119942284"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Scholarship","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.08184","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.08184","pdf_url":"https://arxiv.org/pdf/2402.08184","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8752637606","display_name":null,"funder_award_id":"OAC-1828380","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389315154.pdf"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1589747210","https://openalex.org/W1985697265","https://openalex.org/W2020573190","https://openalex.org/W2076063813","https://openalex.org/W2097381042","https://openalex.org/W2145339207","https://openalex.org/W2156737235","https://openalex.org/W2165347833","https://openalex.org/W2257979135","https://openalex.org/W2296073425","https://openalex.org/W2404399993","https://openalex.org/W2574978968","https://openalex.org/W2576264401","https://openalex.org/W2617547828","https://openalex.org/W2736601468","https://openalex.org/W2749807327","https://openalex.org/W2756196406","https://openalex.org/W2770581177","https://openalex.org/W2921955147","https://openalex.org/W2963628712","https://openalex.org/W2963890729","https://openalex.org/W2966476822","https://openalex.org/W3112288498","https://openalex.org/W3149688139","https://openalex.org/W4206324902","https://openalex.org/W4210638461","https://openalex.org/W4226237817","https://openalex.org/W4286748781","https://openalex.org/W4288594419","https://openalex.org/W4296512904","https://openalex.org/W4299518610","https://openalex.org/W4299802797","https://openalex.org/W6674600207","https://openalex.org/W6682132143","https://openalex.org/W6683195989","https://openalex.org/W6684072715","https://openalex.org/W6685444988","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6743756900","https://openalex.org/W6744537943","https://openalex.org/W6758846586","https://openalex.org/W6840380725"],"related_works":["https://openalex.org/W2475116013","https://openalex.org/W2066741154","https://openalex.org/W2770018148","https://openalex.org/W2358308169","https://openalex.org/W2385135707","https://openalex.org/W2140315382","https://openalex.org/W2059109728","https://openalex.org/W2082556335","https://openalex.org/W322691623","https://openalex.org/W2494989134"],"abstract_inverted_index":{"Multi-Agent":[0,21,121],"Reinforcement":[1],"Learning":[2,153],"(MARL)":[3],"algorithms":[4],"are":[5],"widely":[6],"adopted":[7,150],"in":[8,19,103,113,131,189],"tackling":[9],"complex":[10],"tasks":[11,27],"that":[12,82,96],"require":[13],"collaboration":[14],"and":[15,32,70,125,164,179],"competition":[16],"among":[17],"agents":[18,47,63,144],"dynamic":[20],"Systems":[22],"(MAS).":[23],"However,":[24],"learning":[25,68,85,133,145,158,169,187],"such":[26],"from":[28,58,139,146],"scratch":[29],"is":[30],"arduous":[31],"may":[33],"not":[34],"always":[35],"be":[36],"feasible,":[37],"particularly":[38],"for":[39,86],"MASs":[40],"with":[41],"a":[42,79,107,114],"large":[43],"number":[44],"of":[45,116],"interactive":[46],"due":[48],"to":[49,143,160,184],"the":[50,67,119,126],"extensive":[51],"sample":[52],"complexity.":[53],"Therefore,":[54],"reusing":[55],"knowledge":[56,163,181],"gained":[57],"past":[59],"experiences":[60],"or":[61],"other":[62,140],"could":[64],"efficiently":[65],"accelerate":[66],"process":[69,176],"upscale":[71],"MARL":[72,87],"algorithms.":[73],"In":[74],"this":[75],"study,":[76],"we":[77,149],"introduce":[78],"novel":[80],"framework":[81],"enables":[83],"transfer":[84],"through":[88],"unifying":[89],"various":[90],"state":[91],"spaces":[92],"into":[93],"fixed-size":[94],"inputs":[95],"allow":[97],"one":[98],"unified":[99],"deep-learning":[100],"policy":[101,159],"viable":[102],"different":[104],"scenarios":[105,117,141,170],"within":[106,118],"MAS.":[108],"We":[109],"evaluated":[110],"our":[111,156],"approach":[112],"range":[115],"StarCraft":[120],"Challenge":[122],"(SMAC)":[123],"environment,":[124],"findings":[127],"show":[128],"significant":[129],"enhancements":[130],"multi-agent":[132,186],"performance":[134,188],"using":[135],"maneuvering":[136],"skills":[137,165],"learned":[138],"compared":[142],"scratch.":[147],"Furthermore,":[148],"Curriculum":[151],"Transfer":[152],"(CTL),":[154],"enabling":[155],"deep":[157],"progressively":[161],"acquire":[162],"across":[166],"pre-designed":[167],"homogeneous":[168],"organized":[171],"by":[172],"difficulty":[173],"levels.":[174],"This":[175],"promotes":[177],"inter-":[178],"intra-agent":[180],"transfer,":[182],"leading":[183],"high":[185],"more":[190],"complicated":[191],"heterogeneous":[192],"scenarios.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2023-12-05T00:00:00"}