{"id":"https://openalex.org/W7123352137","doi":"https://doi.org/10.1109/cdc57313.2025.11312253","title":"Optimized State Transition Compressive Representation for Multi-Agent Control via Reinforcement Learning","display_name":"Optimized State Transition Compressive Representation for Multi-Agent Control via Reinforcement Learning","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123352137","doi":"https://doi.org/10.1109/cdc57313.2025.11312253"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","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/A5113304330","display_name":"Mohan Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mohan Niu","raw_affiliation_strings":["Beijing University of Technology,School of Information Science and Technology,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,School of Information Science and Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044018192","display_name":"Jinghao Liu","orcid":"https://orcid.org/0000-0002-5922-1698"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinghao Liu","raw_affiliation_strings":["Beijing University of Technology,School of Information Science and Technology,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,School of Information Science and Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051517054","display_name":"Hongyan Yang","orcid":"https://orcid.org/0000-0003-4755-1857"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyan Yang","raw_affiliation_strings":["Beijing University of Technology,School of Information Science and Technology,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,School of Information Science and Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108058523","display_name":"Fangyu Li","orcid":"https://orcid.org/0000-0002-4908-1150"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangyu Li","raw_affiliation_strings":["Beijing University of Technology,School of Information Science and Technology,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,School of Information Science and Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113304330"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.82676833,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1590","last_page":"1595"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6226000189781189,"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":0.6226000189781189,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.19859999418258667,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.03579999879002571,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6743000149726868},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.5763000249862671},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5580999851226807},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5562999844551086},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5503000020980835},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5351999998092651},{"id":"https://openalex.org/keywords/compressed-sensing","display_name":"Compressed sensing","score":0.5221999883651733},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.48739999532699585},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4796000123023987},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.46720001101493835}],"concepts":[{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6743000149726868},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.5763000249862671},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5580999851226807},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5562999844551086},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5503000020980835},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5351999998092651},{"id":"https://openalex.org/C124851039","wikidata":"https://www.wikidata.org/wiki/Q2665459","display_name":"Compressed sensing","level":2,"score":0.5221999883651733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5080999732017517},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.48739999532699585},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4796000123023987},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.46720001101493835},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.435699999332428},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.42719998955726624},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.41940000653266907},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.3952000141143799},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3817000091075897},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.36800000071525574},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3321000039577484},{"id":"https://openalex.org/C52918065","wikidata":"https://www.wikidata.org/wiki/Q230945","display_name":"State-space representation","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2989000082015991},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.812101423740387,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-agent":[0],"control":[1,78,112],"systems":[2],"require":[3],"compressive":[4,24],"representation":[5,25],"to":[6,58,76,82],"capture":[7],"the":[8,47,68,72,77,87,96],"key":[9],"patterns":[10],"of":[11,89],"state":[12,22,49],"transition":[13,23,36,73],"dynamics":[14,45],"for":[15],"efficient":[16],"decision-making.":[17],"We":[18],"propose":[19],"an":[20,30],"optimized":[21],"(OSTCR)":[26],"method":[27,39,70,103],"by":[28],"embedding":[29],"information":[31,74],"bottleneck":[32],"constraint":[33],"into":[34],"reward-based":[35],"consistency.":[37],"Our":[38],"aligns":[40],"states":[41],"with":[42],"similar":[43],"reward":[44],"in":[46,107],"compressed":[48],"space":[50],"and":[51,61,80,111],"filters":[52],"out":[53],"task-irrelevant":[54],"details":[55],"simultaneously,":[56],"leading":[57],"a":[59,83],"compact":[60],"informative":[62],"representation.":[63],"Theoretical":[64],"analysis":[65],"demonstrates":[66],"that":[67,101],"proposed":[69],"preserves":[71],"relevant":[75],"task":[79],"converges":[81],"representation,":[84],"significantly":[85],"improving":[86],"efficiency":[88],"policy":[90],"learning.":[91],"The":[92],"experiment":[93],"results":[94],"on":[95],"multi-agent":[97],"particle":[98],"environments":[99],"demonstrate":[100],"our":[102],"surpasses":[104],"current":[105],"methods":[106],"both":[108],"convergence":[109],"speed":[110],"performance.":[113]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-14T00:00:00"}