{"id":"https://openalex.org/W7147102754","doi":"https://doi.org/10.48550/arxiv.2603.27450","title":"FlowRL: A Taxonomy and Modular Framework for Reinforcement Learning with Diffusion Policies","display_name":"FlowRL: A Taxonomy and Modular Framework for Reinforcement Learning with Diffusion Policies","publication_year":2026,"publication_date":"2026-03-29","ids":{"openalex":"https://openalex.org/W7147102754","doi":"https://doi.org/10.48550/arxiv.2603.27450"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.27450","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.27450","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.27450","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024132222","display_name":"Chenxiao Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Chenxiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008105452","display_name":"Edward Chen","orcid":"https://orcid.org/0000-0001-8008-8097"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Edward","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132566949","display_name":"Tianyi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Tianyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132679601","display_name":"Bo Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.882099986076355,"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":0.882099986076355,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.006300000008195639,"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":0.005799999926239252,"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":0.7141000032424927},{"id":"https://openalex.org/keywords/agile-software-development","display_name":"Agile software development","score":0.6054999828338623},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.555400013923645},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.5515999794006348},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4458000063896179},{"id":"https://openalex.org/keywords/codebase","display_name":"Codebase","score":0.4230000078678131},{"id":"https://openalex.org/keywords/best-practice","display_name":"Best practice","score":0.3625999987125397}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7141000032424927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7091000080108643},{"id":"https://openalex.org/C14185376","wikidata":"https://www.wikidata.org/wiki/Q30232","display_name":"Agile software development","level":2,"score":0.6054999828338623},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.555400013923645},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.5515999794006348},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.44339999556541443},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.42640000581741333},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.4230000078678131},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35440000891685486},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.33739998936653137},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33090001344680786},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3138999938964844},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.27450","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.27450","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.27450","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.27450","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Thanks":[0],"to":[1,30,47,56,129],"their":[2],"remarkable":[3],"flexibility,":[4],"diffusion":[5],"models":[6,9,165],"and":[7,87,107,115,125,145,157,166],"flow":[8],"have":[10,44],"emerged":[11],"as":[12],"promising":[13],"candidates":[14],"for":[15,36,78,100,127,143,151,161],"policy":[16,38],"representation.":[17],"However,":[18],"efficient":[19],"reinforcement":[20],"learning":[21],"(RL)":[22],"upon":[23],"these":[24,58],"policies":[25],"remains":[26],"a":[27,53,75,92,118,140,148],"challenge":[28],"due":[29],"the":[31,50,135,155],"lack":[32],"of":[33,122],"explicit":[34],"log-probabilities":[35],"vanilla":[37],"gradient":[39],"estimators.":[40],"While":[41],"numerous":[42],"attempts":[43],"been":[45],"proposed":[46],"address":[48],"this,":[49],"field":[51],"lacks":[52],"unified":[54],"perspective":[55],"reconcile":[57],"seemingly":[59],"disparate":[60],"methods,":[61],"thus":[62],"hampering":[63],"ongoing":[64],"development.":[65],"In":[66],"this":[67,71],"paper,":[68],"we":[69,90,104],"bridge":[70],"gap":[72],"by":[73],"introducing":[74],"comprehensive":[76],"taxonomy":[77],"RL":[79],"algorithms":[80,132],"with":[81],"diffusion/flow":[82],"policies.":[83],"To":[84],"support":[85],"reproducibility":[86],"agile":[88],"prototyping,":[89],"introduce":[91],"modular,":[93],"JAX-based":[94],"open-source":[95],"codebase":[96],"that":[97],"leverages":[98],"JIT-compilation":[99],"high-throughput":[101],"training.":[102],"Finally,":[103],"provide":[105],"systematic":[106],"standardized":[108],"benchmarks":[109],"across":[110],"Gym-Locomotion,":[111],"DeepMind":[112],"Control":[113],"Suite,":[114],"IsaacLab,":[116],"offering":[117],"rigorous":[119],"side-by-side":[120],"comparison":[121],"diffusion-based":[123],"methods":[124],"guidance":[126],"practitioners":[128,162],"choose":[130],"proper":[131],"based":[133],"on":[134],"application.":[136],"Our":[137,168],"work":[138],"establishes":[139],"clear":[141],"foundation":[142],"understanding":[144],"algorithm":[146],"design,":[147],"high-efficiency":[149],"toolkit":[150],"future":[152],"research":[153],"in":[154,163],"field,":[156],"an":[158],"algorithmic":[159],"guideline":[160],"generative":[164],"robotics.":[167],"code":[169],"is":[170],"available":[171],"at":[172],"https://github.com/typoverflow/flow-rl.":[173]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-02T00:00:00"}