{"id":"https://openalex.org/W4414693417","doi":"https://doi.org/10.1109/tnse.2025.3616360","title":"Toward Diffusion-Based Deep Reinforcement Learning for Discrete Decision-Making: Methods and Evaluations","display_name":"Toward Diffusion-Based Deep Reinforcement Learning for Discrete Decision-Making: Methods and Evaluations","publication_year":2025,"publication_date":"2025-10-01","ids":{"openalex":"https://openalex.org/W4414693417","doi":"https://doi.org/10.1109/tnse.2025.3616360"},"language":"en","primary_location":{"id":"doi:10.1109/tnse.2025.3616360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnse.2025.3616360","pdf_url":null,"source":{"id":"https://openalex.org/S2484352698","display_name":"IEEE Transactions on Network Science and Engineering","issn_l":"2327-4697","issn":["2327-4697","2334-329X"],"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 Network Science and Engineering","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/A5100457663","display_name":"Zhen Chen","orcid":"https://orcid.org/0000-0002-0444-8828"},"institutions":[{"id":"https://openalex.org/I105126617","display_name":"Zhejiang International Studies University","ror":"https://ror.org/01vwvvq12","country_code":"CN","type":"education","lineage":["https://openalex.org/I105126617"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Chen","raw_affiliation_strings":["Hangzhou International Innovation Institute, Beihang University, Hangzhou, China","School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0444-8828","affiliations":[{"raw_affiliation_string":"Hangzhou International Innovation Institute, Beihang University, Hangzhou, China","institution_ids":["https://openalex.org/I105126617","https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiao Long","orcid":"https://orcid.org/0009-0008-7108-3655"},"institutions":[{"id":"https://openalex.org/I105126617","display_name":"Zhejiang International Studies University","ror":"https://ror.org/01vwvvq12","country_code":"CN","type":"education","lineage":["https://openalex.org/I105126617"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Long","raw_affiliation_strings":["Hangzhou International Innovation Institute, Beihang University, Hangzhou, China","School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-7108-3655","affiliations":[{"raw_affiliation_string":"Hangzhou International Innovation Institute, Beihang University, Hangzhou, China","institution_ids":["https://openalex.org/I105126617","https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418969","display_name":"Zhang Li","orcid":"https://orcid.org/0000-0003-1989-6102"},"institutions":[{"id":"https://openalex.org/I105126617","display_name":"Zhejiang International Studies University","ror":"https://ror.org/01vwvvq12","country_code":"CN","type":"education","lineage":["https://openalex.org/I105126617"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Zhang","raw_affiliation_strings":["Hangzhou International Innovation Institute, Beihang University, Hangzhou, China","Hangzhou International Innovation Institute of Beihang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1989-6102","affiliations":[{"raw_affiliation_string":"Hangzhou International Innovation Institute, Beihang University, Hangzhou, China","institution_ids":["https://openalex.org/I105126617","https://openalex.org/I82880672"]},{"raw_affiliation_string":"Hangzhou International Innovation Institute of Beihang University, Hangzhou, China","institution_ids":["https://openalex.org/I105126617"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036580072","display_name":"Wentong Cai","orcid":"https://orcid.org/0000-0002-0183-3835"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wentong Cai","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0183-3835","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0447,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.77709707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"13","issue":null,"first_page":"4406","last_page":"4421"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.5963000059127808,"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"}},"topics":[{"id":"https://openalex.org/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.5963000059127808,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7581999897956848},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5740000009536743},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5094000101089478},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4675000011920929},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4661000072956085},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.45339998602867126},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4359000027179718},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.3785000145435333}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7581999897956848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7416999936103821},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5740000009536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5303000211715698},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5094000101089478},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4675000011920929},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4661000072956085},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.45339998602867126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4422000050544739},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4359000027179718},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.3571000099182129},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.3296999931335449},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2892000079154968},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C13736549","wikidata":"https://www.wikidata.org/wiki/Q4489420","display_name":"Industrial engineering","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2766000032424927},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.26170000433921814},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.259799987077713}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tnse.2025.3616360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnse.2025.3616360","pdf_url":null,"source":{"id":"https://openalex.org/S2484352698","display_name":"IEEE Transactions on Network Science and Engineering","issn_l":"2327-4697","issn":["2327-4697","2334-329X"],"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 Network Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8209592694","display_name":null,"funder_award_id":"62373026","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2746553466","https://openalex.org/W2752189352","https://openalex.org/W2951360122","https://openalex.org/W2953169926","https://openalex.org/W3037201895","https://openalex.org/W3113891126","https://openalex.org/W3170112077","https://openalex.org/W4283211351","https://openalex.org/W4284711157","https://openalex.org/W4293215149","https://openalex.org/W4318773873","https://openalex.org/W4383752013","https://openalex.org/W4385287226","https://openalex.org/W4387195417","https://openalex.org/W4387914688","https://openalex.org/W4390872396","https://openalex.org/W4391019625","https://openalex.org/W4391468387","https://openalex.org/W4391621086","https://openalex.org/W4396817538","https://openalex.org/W4402350838","https://openalex.org/W4402473949","https://openalex.org/W4404048113","https://openalex.org/W4405755397","https://openalex.org/W4407132496","https://openalex.org/W4407390684","https://openalex.org/W4408823648","https://openalex.org/W4409057813","https://openalex.org/W4410242187","https://openalex.org/W4410358938","https://openalex.org/W4411746735","https://openalex.org/W4413581216","https://openalex.org/W4416750291"],"related_works":[],"abstract_inverted_index":{"Discrete":[0],"decision-making":[1,97],"problems,":[2],"such":[3,34],"as":[4,28,140,207],"combinatorial":[5,167],"optimization":[6],"tasks":[7],"frequently":[8],"encountered":[9],"in":[10,19,58,192,196],"network":[11],"science":[12],"and":[13,41,54,109,128,154,172,200],"industrial":[14,174],"IoT":[15],"systems,":[16],"are":[17,112],"pervasive":[18],"real-world":[20],"applications.":[21],"Deep":[22],"reinforcement":[23],"learning":[24,110],"(DRL)":[25],"has":[26],"emerged":[27],"a":[29,77,90,116,125,129],"promising":[30],"approach":[31,94,188],"for":[32,39,80,95,218],"addressing":[33],"challenges,":[35],"offering":[36],"the":[37,143,178,182],"potential":[38],"adaptive":[40],"scalable":[42],"solutions.":[43],"However,":[44],"existing":[45],"DRL":[46,93,217],"methods":[47],"often":[48],"suffer":[49],"from":[50],"limited":[51],"policy":[52,83,106,149],"expressiveness":[53],"inefficient":[55],"exploration,":[56],"particularly":[57,195],"discrete":[59,96],"action":[60],"spaces.":[61,220],"Diffusion":[62],"models,":[63],"with":[64,151],"their":[65],"ability":[66],"to":[67,104,147],"construct":[68],"rich":[69],"intermediate":[70],"representations":[71],"through":[72],"iterative":[73],"denoising":[74,100],"processes,":[75],"offer":[76,190],"compelling":[78],"alternative":[79],"enhancing":[81],"discrete-action":[82,219],"learning.":[84],"In":[85],"this":[86,186],"work,":[87],"we":[88],"propose":[89],"diffusion-based":[91],"online":[92,122,216],"spaces,":[98],"employing":[99],"diffusion":[101],"implicit":[102],"models":[103],"accelerate":[105],"inference.":[107],"Exploration":[108],"efficiency":[111],"further":[113],"enhanced":[114],"by":[115],"hybrid":[117],"memory":[118],"system":[119],"comprising":[120],"an":[121,173,208],"replay":[123],"buffer,":[124,127,132],"diffusion-specific":[126],"high-return":[130],"trajectory":[131],"within":[133],"which":[134],"critic-guided":[135],"logit":[136],"construction":[137],"is":[138,160,205],"integrated":[139],"part":[141],"of":[142],"overall":[144],"training":[145],"pipeline":[146],"align":[148],"targets":[150],"both":[152],"value-based":[153],"expert":[155],"signals.":[156],"The":[157,203],"proposed":[158],"method":[159],"evaluated":[161],"on":[162],"selected":[163],"Gym":[164],"benchmarks,":[165],"classical":[166],"problems":[168],"(CVRP,":[169],"Knapsack,":[170],"GraphColoring),":[171],"scheduling":[175],"scenario.":[176],"While":[177],"findings":[179],"remain":[180],"preliminary,":[181],"results":[183],"suggest":[184],"that":[185],"generative":[187,213],"may":[189],"benefits":[191],"certain":[193],"contexts,":[194],"improving":[197],"convergence":[198],"dynamics":[199],"solution":[201],"robustness.":[202],"framework":[204],"intended":[206],"initial":[209],"step":[210],"toward":[211],"integrating":[212],"modeling":[214],"into":[215]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}