{"id":"https://openalex.org/W7127641991","doi":"https://doi.org/10.1145/3769002.3769985","title":"Representation Learning For Efficient Deep Multi-Agent Reinforcement Learning","display_name":"Representation Learning For Efficient Deep Multi-Agent Reinforcement Learning","publication_year":2025,"publication_date":"2025-11-16","ids":{"openalex":"https://openalex.org/W7127641991","doi":"https://doi.org/10.1145/3769002.3769985"},"language":null,"primary_location":{"id":"doi:10.1145/3769002.3769985","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769002.3769985","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3769002.3769985","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067368117","display_name":"Dom Huh","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dom Huh","raw_affiliation_strings":["University of California, Davis, Davis, California, USA"],"raw_orcid":"https://orcid.org/0009-0007-9513-3285","affiliations":[{"raw_affiliation_string":"University of California, Davis, Davis, California, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049559253","display_name":"P. Mohapatra","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasan Mohapatra","raw_affiliation_strings":["UC Davis, Davis, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-2768-5308","affiliations":[{"raw_affiliation_string":"UC Davis, Davis, California, USA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I84218800"],"apc_list":null,"apc_paid":null,"fwci":1.6508,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90994357,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":97},"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":0.8665000200271606,"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":0.8665000200271606,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.022600000724196434,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.019200000911951065,"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":0.8083000183105469},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6958000063896179},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5935999751091003},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5601000189781189},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5099999904632568},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4413999915122986},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4350999891757965},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.4300000071525574},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.3797999918460846}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8083000183105469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6988999843597412},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6958000063896179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.676800012588501},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6536999940872192},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5935999751091003},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5601000189781189},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5099999904632568},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4413999915122986},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4350999891757965},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.4300000071525574},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.3384999930858612},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.3382999897003174},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.29989999532699585},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.27880001068115234},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.2766000032424927},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3769002.3769985","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769002.3769985","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3769002.3769985","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769002.3769985","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1491843047","https://openalex.org/W2575731723","https://openalex.org/W3209969885","https://openalex.org/W4386738330"],"related_works":[],"abstract_inverted_index":{"Sample":[0],"efficiency":[1,103],"remains":[2],"a":[3,24,29,53,59,71,123],"key":[4],"challenge":[5],"in":[6,52,101],"multi-agent":[7,49,60,127],"reinforcement":[8],"learning":[9,28,36,68,105],"(MARL).":[10],"To":[11],"address":[12],"this,":[13],"we":[14,97],"introduce":[15],"MAPO-LSO":[16,57,115],"(Multi-Agent":[17],"Policy":[18],"Optimization":[19],"with":[20,111],"Latent":[21],"Space":[22],"Optimization),":[23],"novel":[25],"approach":[26],"to":[27,38,69,87,107],"meaningful":[30],"latent":[31,72],"representation":[32],"space":[33],"through":[34],"auxiliary":[35],"objectives":[37],"supplement":[39],"MARL":[40,109,119],"training":[41],"by":[42],"leveraging":[43],"various":[44],"nuanced":[45],"facets":[46],"of":[47,62,114,126],"the":[48,112],"control":[50,91,128],"dynamics":[51,64],"self-supervised":[54],"manner.":[55],"Specifically,":[56],"proposes":[58],"application":[61],"transition":[63],"reconstruction":[65],"and":[66,83,104],"self-predictive":[67],"construct":[70],"state":[73],"optimization":[74],"scheme":[75],"that":[76],"captures":[77],"underlying":[78],"relationships":[79],"within":[80],"their":[81],"environment":[82],"population,":[84],"ultimately":[85],"leading":[86],"more":[88],"effective":[89],"joint":[90],"policies.":[92],"Through":[93],"extensive":[94],"empirical":[95],"experimentation,":[96],"affirm":[98],"notable":[99],"improvements":[100],"sample":[102],"performance":[106],"deep":[108],"algorithms":[110],"addition":[113],"without":[116],"any":[117],"additional":[118],"hyperparameter":[120],"tuning":[121],"on":[122],"diverse":[124],"suite":[125],"tasks.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-02-06T00:00:00"}