{"id":"https://openalex.org/W7138222050","doi":"https://doi.org/10.1609/aaai.v40i28.39537","title":"CHDP: Cooperative Hybrid Diffusion Policies for Reinforcement Learning in Parameterized Action Space","display_name":"CHDP: Cooperative Hybrid Diffusion Policies for Reinforcement Learning in Parameterized Action Space","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138222050","doi":"https://doi.org/10.1609/aaai.v40i28.39537"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i28.39537","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i28.39537","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i28.39537","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129668801","display_name":"Bingyi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bingyi Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060046434","display_name":"Jinbo He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinbo He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028213488","display_name":"Haiyong Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haiyong Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129712563","display_name":"Enshu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Enshu Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129703004","display_name":"Weizhen Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weizhen Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129739807","display_name":"Jingxiang Hao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingxiang Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129684674","display_name":"Peixi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peixi Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129751064","display_name":"Zhuangzhuang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuangzhuang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20374508,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"28","first_page":"23640","last_page":"23648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9620000123977661,"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":0.9620000123977661,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.005400000140070915,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.00430000014603138,"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/leverage","display_name":"Leverage (statistics)","score":0.723800003528595},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6195999979972839},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5756000280380249},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45320001244544983},{"id":"https://openalex.org/keywords/discrete-space","display_name":"Discrete space","score":0.4417000114917755},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.41589999198913574},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.41499999165534973},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4011000096797943}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.723800003528595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6577000021934509},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6195999979972839},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5756000280380249},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45320001244544983},{"id":"https://openalex.org/C153782549","wikidata":"https://www.wikidata.org/wiki/Q175116","display_name":"Discrete space","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.39250001311302185},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3813000023365021},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34689998626708984},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.34200000762939453},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C2778079155","wikidata":"https://www.wikidata.org/wiki/Q288500","display_name":"Potential game","level":3,"score":0.29339998960494995},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2922999858856201},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.2896000146865845},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26579999923706055},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i28.39537","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i28.39537","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/39537","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/39537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i28.39537","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i28.39537","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"No poverty","score":0.40227189660072327,"id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Hybrid":[0,66],"action":[1,28,54,123,157,166,208],"space,":[2,158],"which":[3],"combines":[4],"discrete":[5,82,96,156,177,200],"choices":[6],"and":[7,18,24,40,62,83],"continuous":[8,85,90],"parameters,":[9],"is":[10,92],"prevalent":[11],"in":[12,43,120,135,154,181,218],"domains":[13],"such":[14],"as":[15,57],"robot":[16],"control":[17],"game":[19,61],"AI.":[20],"However,":[21],"efficiently":[22],"modeling":[23,100],"optimizing":[25],"hybrid":[26,53,207],"discrete-continuous":[27],"space":[29,55,167],"remains":[30],"a":[31,58,64,81,84,141,161,169,182,189],"fundamental":[32],"challenge,":[33,49],"mainly":[34],"due":[35],"to":[36,71,112,116,149,179,193,216],"limited":[37],"policy":[38,91,133,178],"expressiveness":[39,115],"poor":[41],"scalability":[42,151],"high-dimensional":[44,155],"settings.":[45],"To":[46,125],"address":[47],"this":[48,136],"we":[50,139,159,187],"view":[51],"the":[52,95,101,109,127,165,176,195,199],"problem":[56],"fully":[59],"cooperative":[60,77,106,137],"propose":[63],"Cooperative":[65],"Diffusion":[67],"Policies":[68],"(CHDP)":[69],"framework":[70],"solve":[72],"it.":[73],"CHDP":[74,210],"employs":[75],"two":[76],"agents":[78],"that":[79,145,163],"leverage":[80,113],"diffusion":[86,110],"policy,":[87],"respectively.":[88],"The":[89],"conditioned":[93],"on":[94],"action's":[97],"representation,":[98],"explicitly":[99],"dependency":[102],"between":[103],"them.":[104],"This":[105,173],"design":[107,188],"allows":[108],"policies":[111],"their":[114,121],"capture":[117],"complex":[118],"distributions":[119],"respective":[122],"spaces.":[124],"mitigate":[126],"update":[128,143],"conflicts":[129],"arising":[130],"from":[131],"simultaneous":[132],"updates":[134],"setting,":[138],"employ":[140],"sequential":[142],"scheme":[144],"fosters":[146],"co-adaptation.":[147],"Moreover,":[148],"improve":[150],"when":[152],"learning":[153],"construct":[160],"codebook":[162],"embeds":[164],"into":[168],"low-dimensional":[170],"latent":[171],"space.":[172,185],"mapping":[174],"enables":[175],"learn":[180],"compact,":[183],"structured":[184],"Finally,":[186],"Q-function-based":[190],"guidance":[191],"mechanism":[192],"align":[194],"codebook's":[196],"embeddings":[197],"with":[198],"policy's":[201],"representation":[202],"during":[203],"training.":[204],"On":[205],"challenging":[206],"benchmarks,":[209],"outperforms":[211],"state-of-the-art":[212],"method":[213],"by":[214],"up":[215],"19.3%":[217],"success":[219],"rate.":[220]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}