{"id":"https://openalex.org/W4387885940","doi":"https://doi.org/10.1109/tcds.2023.3326297","title":"State Augmentation via Self-Supervision in Offline Multiagent Reinforcement Learning","display_name":"State Augmentation via Self-Supervision in Offline Multiagent Reinforcement Learning","publication_year":2023,"publication_date":"2023-10-23","ids":{"openalex":"https://openalex.org/W4387885940","doi":"https://doi.org/10.1109/tcds.2023.3326297"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2023.3326297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2023.3326297","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-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/A5002463311","display_name":"Siying Wang","orcid":"https://orcid.org/0000-0002-3180-0815"},"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":true,"raw_author_name":"Siying Wang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102488433","display_name":"Xiaodie 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":"Xiaodie Li","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021975286","display_name":"Hong Qu","orcid":"https://orcid.org/0000-0001-6114-3441"},"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":"Hong Qu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100687323","display_name":"Wenyu Chen","orcid":"https://orcid.org/0000-0002-9933-8014"},"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":"Wenyu Chen","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002463311"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.6938,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76425203,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"16","issue":"3","first_page":"1051","last_page":"1062"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.944100022315979,"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":0.9399999976158142,"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":0.9049351215362549},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.798314094543457},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5572799444198608},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5435656309127808},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.532073974609375},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.49069273471832275},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4787006676197052},{"id":"https://openalex.org/keywords/extrapolation","display_name":"Extrapolation","score":0.45107904076576233},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.43073561787605286},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41590675711631775},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41263115406036377},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10262754559516907},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06017667055130005}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9049351215362549},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.798314094543457},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5572799444198608},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5435656309127808},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.532073974609375},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.49069273471832275},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4787006676197052},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.45107904076576233},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.43073561787605286},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41590675711631775},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41263115406036377},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10262754559516907},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06017667055130005},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2023.3326297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2023.3326297","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7167048579","display_name":null,"funder_award_id":"61976043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8323016548","display_name":null,"funder_award_id":"62236007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W2037067712","https://openalex.org/W2088595989","https://openalex.org/W2124861983","https://openalex.org/W2145339207","https://openalex.org/W2177818176","https://openalex.org/W2740377041","https://openalex.org/W2747213132","https://openalex.org/W2760661167","https://openalex.org/W2786010338","https://openalex.org/W2803208334","https://openalex.org/W2959091704","https://openalex.org/W2963658727","https://openalex.org/W2963762747","https://openalex.org/W2963864421","https://openalex.org/W2991355586","https://openalex.org/W2993185773","https://openalex.org/W2997103132","https://openalex.org/W2997756730","https://openalex.org/W3015437096","https://openalex.org/W3016330197","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3042468599","https://openalex.org/W3097268408","https://openalex.org/W3099427826","https://openalex.org/W3113470404","https://openalex.org/W3121078556","https://openalex.org/W3136817238","https://openalex.org/W3169363132","https://openalex.org/W3175558129","https://openalex.org/W3198999478","https://openalex.org/W4200632533","https://openalex.org/W4213246061","https://openalex.org/W4287756699","https://openalex.org/W4287997992","https://openalex.org/W4301501993","https://openalex.org/W6677939520","https://openalex.org/W6684921986","https://openalex.org/W6728155968","https://openalex.org/W6738796088","https://openalex.org/W6742529797","https://openalex.org/W6749304979","https://openalex.org/W6752380930","https://openalex.org/W6757469721","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6763173156","https://openalex.org/W6763704811","https://openalex.org/W6766805167","https://openalex.org/W6769609827","https://openalex.org/W6771270455","https://openalex.org/W6771428195","https://openalex.org/W6771670691","https://openalex.org/W6771740491","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6776867236","https://openalex.org/W6779265984","https://openalex.org/W6779656125","https://openalex.org/W6792049622","https://openalex.org/W6796289742","https://openalex.org/W6796791731","https://openalex.org/W6796880758","https://openalex.org/W6797702751","https://openalex.org/W6801801719","https://openalex.org/W6802002411","https://openalex.org/W6804100093","https://openalex.org/W6805311634","https://openalex.org/W6810745647","https://openalex.org/W6839526036","https://openalex.org/W6843543632","https://openalex.org/W6864424756"],"related_works":["https://openalex.org/W1968270095","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W2579634771","https://openalex.org/W2034019356"],"abstract_inverted_index":{"The":[0,79,162],"utilization":[1],"of":[2,11,85,113,122,125,140,159,173,182],"pre-collected":[3],"offline":[4,55,89,152,183],"datasets":[5],"for":[6,31],"learning":[7,17,34,186],"in":[8,23,108,137,178,187],"the":[9,38,46,52,63,77,83,102,111,120,134,138,144,157,171,174,180,188],"absence":[10],"environmental":[12],"interaction":[13],"has":[14],"enabled":[15],"reinforcement":[16,33,185],"(RL)":[18],"to":[19,51,62,72,76,95,101,110,133],"make":[20],"significant":[21],"strides":[22],"real-world":[24],"circumstances.":[25],"This":[26],"approach":[27],"is":[28,99],"also":[29],"attractive":[30],"multi-agent":[32,56,96,153,184],"(MARL)":[35],"tasks,":[36],"given":[37],"complex":[39],"interactions":[40],"that":[41,106,129],"occur":[42],"between":[43],"agents":[44],"and":[45,66],"environment.":[47,78],"However,":[48],"when":[49],"compared":[50],"single-agent":[53,93],"approach,":[54],"RL":[57,90],"faces":[58],"more":[59],"challenges":[60],"due":[61,100],"larger":[64],"state":[65,135,189],"action":[67],"space,":[68],"particularly":[69],"with":[70,149],"regard":[71],"poor":[73],"out-of-distribution":[74],"generalization":[75],"present":[80],"study":[81],"demonstrates":[82],"ineffectiveness":[84],"directly":[86],"transferring":[87],"conservative":[88],"algorithms":[91],"from":[92],"settings":[94],"environments,":[97],"which":[98],"accumulating":[103],"extrapolation":[104],"errors":[105],"increase":[107],"proportion":[109],"number":[112],"agents.":[114],"In":[115],"this":[116],"paper,":[117],"we":[118,155],"explore":[119],"efficacy":[121],"three":[123],"types":[124],"data":[126,146,175],"augmentation":[127,147,176],"techniques":[128,148,177],"can":[130],"be":[131],"applied":[132],"representation":[136],"context":[139],"MARL.":[141],"By":[142],"combining":[143],"proposed":[145],"a":[150],"state-of-the-art":[151],"algorithm,":[154],"improve":[156],"function-approximation":[158],"centralized":[160],"Q-networks.":[161],"experimental":[163],"results":[164],"conducted":[165],"on":[166],"StarCraft":[167],"II":[168],"strongly":[169],"support":[170],"effectiveness":[172],"enhancing":[179],"performance":[181],"space.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-07T14:57:38.498316","created_date":"2025-10-10T00:00:00"}