{"id":"https://openalex.org/W4413945284","doi":"https://doi.org/10.1109/icra55743.2025.11128572","title":"AERAS: Adaptive Experience Replay with Attention-Based Sequence Embedding for Improved Multi-Agent Reinforcement Learning","display_name":"AERAS: Adaptive Experience Replay with Attention-Based Sequence Embedding for Improved Multi-Agent Reinforcement Learning","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413945284","doi":"https://doi.org/10.1109/icra55743.2025.11128572"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128572","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128572","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 Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5027931296","display_name":"Zaipeng Xie","orcid":"https://orcid.org/0000-0003-1637-1511"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zaipeng Xie","raw_affiliation_strings":["Hohai University,Key Laboratory of Water Big Data Technology of the Ministry of Water Resources,Nanjing,China,211100"],"affiliations":[{"raw_affiliation_string":"Hohai University,Key Laboratory of Water Big Data Technology of the Ministry of Water Resources,Nanjing,China,211100","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027713037","display_name":"Sitong Shen","orcid":"https://orcid.org/0009-0003-4841-8414"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sitong Shen","raw_affiliation_strings":["Hohai University,Key Laboratory of Water Big Data Technology of the Ministry of Water Resources,Nanjing,China,211100"],"affiliations":[{"raw_affiliation_string":"Hohai University,Key Laboratory of Water Big Data Technology of the Ministry of Water Resources,Nanjing,China,211100","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005326053","display_name":"Yaowu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaowu Wang","raw_affiliation_strings":["Hohai University,Key Laboratory of Water Big Data Technology of the Ministry of Water Resources,Nanjing,China,211100"],"affiliations":[{"raw_affiliation_string":"Hohai University,Key Laboratory of Water Big Data Technology of the Ministry of Water Resources,Nanjing,China,211100","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048888410","display_name":"Wenhao Fang","orcid":"https://orcid.org/0000-0002-2449-3749"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Fang","raw_affiliation_strings":["Hohai University,Key Laboratory of Water Big Data Technology of the Ministry of Water Resources,Nanjing,China,211100"],"affiliations":[{"raw_affiliation_string":"Hohai University,Key Laboratory of Water Big Data Technology of the Ministry of Water Resources,Nanjing,China,211100","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007530002","display_name":"Wen\u2010Zhan Song","orcid":"https://orcid.org/0000-0001-8174-1772"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"WenZhan Song","raw_affiliation_strings":["Center for Cyber-Physical Systems, University of Georgia,Athens,GA,USA,30602"],"affiliations":[{"raw_affiliation_string":"Center for Cyber-Physical Systems, University of Georgia,Athens,GA,USA,30602","institution_ids":["https://openalex.org/I165733156"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027931296"],"corresponding_institution_ids":["https://openalex.org/I163340411"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13580798,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1156","last_page":"1162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9387999773025513,"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":0.9387999773025513,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9269999861717224,"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":0.8599106073379517},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.72669917345047},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6294022798538208},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6282790899276733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46425917744636536},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4128724932670593},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.341230183839798},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3285439610481262},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13595202565193176},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.05581220984458923}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8599106073379517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.72669917345047},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6294022798538208},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6282790899276733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46425917744636536},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4128724932670593},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.341230183839798},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3285439610481262},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13595202565193176},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.05581220984458923},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128572","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128572","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 Robotics and Automation (ICRA)","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":8,"referenced_works":["https://openalex.org/W2292533394","https://openalex.org/W2747213132","https://openalex.org/W2997502221","https://openalex.org/W3156295478","https://openalex.org/W4317987702","https://openalex.org/W4327571609","https://openalex.org/W4387185416","https://openalex.org/W4393906088"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W2966686650"],"abstract_inverted_index":{"Multi-agent":[0],"systems":[1],"in":[2,18,72,114,123],"non-stationary":[3,125],"environments":[4,87,126],"face":[5],"challenges":[6],"due":[7],"to":[8,13,45],"rapidly":[9],"changing":[10],"dynamics,":[11],"leading":[12],"quick":[14],"obsolescence":[15],"of":[16,64,108],"experiences":[17,47,59],"the":[19,27,62,78,105],"replay":[20],"buffer.":[21],"To":[22],"address":[23],"this,":[24],"we":[25],"propose":[26],"Adaptive":[28],"Experience":[29],"Replay":[30],"with":[31,41],"Attention-Based":[32],"Sequence":[33],"Embedding":[34],"(AERAS)":[35],"framework,":[36],"which":[37],"integrates":[38],"sequence":[39,109],"embedding":[40,110],"an":[42],"attention":[43,112],"mechanism":[44],"prioritize":[46],"based":[48],"on":[49,77],"their":[50],"relevance.":[51],"By":[52],"assigning":[53],"adaptive":[54],"weights,":[55],"AERAS":[56,90],"emphasizes":[57],"relevant":[58],"while":[60],"diminishing":[61],"impact":[63],"outdated":[65],"ones,":[66],"enhancing":[67],"efficiency":[68],"and":[69,83,98,111,118],"learning":[70],"performance":[71],"multi-agent":[73,128],"reinforcement":[74],"learning.":[75],"Evaluations":[76],"StarCraft":[79],"II":[80],"Multi-Agent":[81],"Challenge":[82],"Google":[84],"Research":[85],"Football":[86],"show":[88],"that":[89],"consistently":[91],"outperforms":[92],"state-of-the-art":[93],"methods,":[94],"achieving":[95],"faster":[96],"convergence":[97],"higher":[99],"win":[100],"rates.":[101],"Ablation":[102],"studies":[103],"confirm":[104],"essential":[106],"roles":[107],"mechanisms":[113],"boosting":[115],"AERAS's":[116],"robustness":[117],"adaptability,":[119],"underscoring":[120],"its":[121],"effectiveness":[122],"managing":[124],"within":[127],"systems.":[129]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}