{"id":"https://openalex.org/W4402953784","doi":"https://doi.org/10.48550/arxiv.2409.00588","title":"Diffusion Policy Policy Optimization","display_name":"Diffusion Policy Policy Optimization","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402953784","doi":"https://doi.org/10.48550/arxiv.2409.00588"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2409.00588","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.00588","pdf_url":"https://arxiv.org/pdf/2409.00588","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.00588","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000576583","display_name":"Allen Z. Ren","orcid":"https://orcid.org/0000-0001-5306-2844","observed_orcids":["https://orcid.org/0000-0001-5306-2844"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ren, Allen Z.","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060177564","display_name":"Justin Lidard","orcid":"https://orcid.org/0000-0001-8316-1018","observed_orcids":["https://orcid.org/0000-0001-8316-1018"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lidard, Justin","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082607188","display_name":"Lars Ankile","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankile, Lars L.","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026449499","display_name":"Anthony Simeonov","orcid":"https://orcid.org/0000-0002-2573-2510","observed_orcids":["https://orcid.org/0000-0002-2573-2510"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simeonov, Anthony","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111774389","display_name":"Pulkit Agrawal","orcid":"https://orcid.org/0000-0001-8463-9917","observed_orcids":["https://orcid.org/0000-0001-8463-9917","https://orcid.org/0000-0002-9569-6690"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Agrawal, Pulkit","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102792178","display_name":"Anirudha Majumdar","orcid":"https://orcid.org/0009-0002-2296-7485","observed_orcids":["https://orcid.org/0009-0002-2296-7485","https://orcid.org/0000-0002-9383-6071"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Majumdar, Anirudha","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091048694","display_name":"Benjamin Burchfiel","orcid":"https://orcid.org/0000-0001-7332-6712","observed_orcids":["https://orcid.org/0000-0001-7332-6712"]},"institutions":[{"id":"https://openalex.org/I4391768151","display_name":"Toyota Research Institute","ror":"https://ror.org/04fpkc108","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4391768151"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Burchfiel, Benjamin","raw_affiliation_strings":["Toyota Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Research Institute","institution_ids":["https://openalex.org/I4391768151"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039615570","display_name":"Hongkai Dai","orcid":"https://orcid.org/0000-0002-6131-3620","observed_orcids":["https://orcid.org/0000-0002-6131-3620"]},"institutions":[{"id":"https://openalex.org/I4391768151","display_name":"Toyota Research Institute","ror":"https://ror.org/04fpkc108","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4391768151"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dai, Hongkai","raw_affiliation_strings":["Toyota Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Research Institute","institution_ids":["https://openalex.org/I4391768151"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037154191","display_name":"Max Simchowitz","orcid":"https://orcid.org/0000-0001-9900-1238","observed_orcids":["https://orcid.org/0000-0001-9900-1238"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simchowitz, Max","raw_affiliation_strings":["Carnegie Mellon University","Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":221,"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":1.0,"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":1.0,"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":0.0,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"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/policy-optimization","display_name":"policy optimization","score":0.6000000238418579},{"id":"https://openalex.org/keywords/continuous-control","display_name":"continuous control","score":0.8399999737739563},{"id":"https://openalex.org/keywords/robot-learning","display_name":"robot learning","score":0.9399999976158142},{"id":"https://openalex.org/keywords/diffusion-policy","display_name":"diffusion policy","score":0.4830000102519989},{"id":"https://openalex.org/keywords/policy-robustness","display_name":"policy robustness","score":0.8489999771118164},{"id":"https://openalex.org/keywords/zero-shot-deployment","display_name":"zero-shot deployment","score":0.6650000214576721},{"id":"https://openalex.org/keywords/simulation-to-robot-transfer","display_name":"simulation-to-robot transfer","score":0.7200000286102295}],"concepts":[{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6833711862564087},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.3613561987876892},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.3304009437561035},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.14104092121124268},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12257140874862671}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2409.00588","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.00588","pdf_url":"https://arxiv.org/pdf/2409.00588","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.00588","doi":"https://doi.org/10.48550/arxiv.2409.00588","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.00588","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.00588","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.00588","pdf_url":"https://arxiv.org/pdf/2409.00588","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315934","display_name":"Toyota Research Institute","ror":"https://ror.org/04fpkc108"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402953784.pdf","grobid_xml":"https://content.openalex.org/works/W4402953784.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W2173248099","https://openalex.org/W2736601468","https://openalex.org/W2741122588","https://openalex.org/W2757631751","https://openalex.org/W2978455699","https://openalex.org/W2981701630","https://openalex.org/W3016525976","https://openalex.org/W3034786558","https://openalex.org/W3037207827","https://openalex.org/W3038871683","https://openalex.org/W3087665158","https://openalex.org/W3092442149","https://openalex.org/W3110257065","https://openalex.org/W3171801597","https://openalex.org/W3187722890","https://openalex.org/W3193576605","https://openalex.org/W4281398962","https://openalex.org/W4281661031","https://openalex.org/W4291960900","https://openalex.org/W4298183794","https://openalex.org/W4298187450","https://openalex.org/W4303440777","https://openalex.org/W4318242039","https://openalex.org/W4318903518","https://openalex.org/W4319323815","https://openalex.org/W4366850766","https://openalex.org/W4377865266","https://openalex.org/W4378464471","https://openalex.org/W4380136171","https://openalex.org/W4385430497","https://openalex.org/W4385430582","https://openalex.org/W4385430633","https://openalex.org/W4385430674","https://openalex.org/W4386501368","https://openalex.org/W4386793378","https://openalex.org/W4387294554","https://openalex.org/W4387295800","https://openalex.org/W4387560742","https://openalex.org/W4388327372","https://openalex.org/W4388482290","https://openalex.org/W4389814346","https://openalex.org/W4390041653","https://openalex.org/W4390635563","https://openalex.org/W4392120962","https://openalex.org/W4392538920","https://openalex.org/W4394709627","https://openalex.org/W4401416214","https://openalex.org/W4401417422","https://openalex.org/W4402354084","https://openalex.org/W4402354100","https://openalex.org/W4402354171","https://openalex.org/W4402753790","https://openalex.org/W4405556646","https://openalex.org/W4413918134","https://openalex.org/W4415798523","https://openalex.org/W4415800813"],"related_works":["https://openalex.org/W7204072027","https://openalex.org/W7115685940","https://openalex.org/W4415200532","https://openalex.org/W6891796058","https://openalex.org/W7119141932","https://openalex.org/W7213136359","https://openalex.org/W7162799466","https://openalex.org/W7164167083","https://openalex.org/W7164848801","https://openalex.org/W4403665798"],"abstract_inverted_index":{"We":[0,127],"introduce":[1],"Diffusion":[2,18],"Policy":[3,4],"Optimization,":[5],"DPPO,":[6],"an":[7],"algorithmic":[8],"framework":[9],"including":[10,140],"best":[11],"practices":[12],"for":[13,58,73,83],"fine-tuning":[14,74,91,110],"diffusion-based":[15,59,84],"policies":[16,44,85,153],"(e.g.":[17],"Policy)":[19],"in":[20,41,75,134,157],"continuous":[21],"control":[22],"and":[23,71,86,111,118,123,147],"robot":[24,155],"learning":[25,35],"tasks":[26,143],"using":[27],"the":[28,67,112,130],"policy":[29,47,94,125],"gradient":[30],"(PG)":[31],"method":[32],"from":[33],"reinforcement":[34],"(RL).":[36],"PG":[37,90],"methods":[38,82],"are":[39],"ubiquitous":[40],"training":[42],"RL":[43,81,109],"with":[45,144,164],"other":[46,80,93],"parameterizations;":[48],"nevertheless,":[49],"they":[50],"had":[51],"been":[52],"conjectured":[53],"to":[54,79,89,116],"be":[55],"less":[56],"efficient":[57],"policies.":[60],"Surprisingly,":[61],"we":[62,99],"show":[63],"that":[64,101],"DPPO":[65,102,133],"achieves":[66],"strongest":[68],"overall":[69],"performance":[70],"efficiency":[72],"common":[76],"benchmarks":[77],"compared":[78,88],"also":[87],"of":[92,105,132,137,151],"parameterizations.":[95],"Through":[96],"experimental":[97],"investigation,":[98],"find":[100],"takes":[103],"advantage":[104],"unique":[106],"synergies":[107],"between":[108],"diffusion":[113],"parameterization,":[114],"leading":[115],"structured":[117],"on-manifold":[119],"exploration,":[120],"stable":[121],"training,":[122],"strong":[124],"robustness.":[126],"further":[128],"demonstrate":[129],"strengths":[131],"a":[135,158],"range":[136],"realistic":[138],"settings,":[139],"simulated":[141],"robotic":[142],"pixel":[145],"observations,":[146],"via":[148],"zero-shot":[149],"deployment":[150],"simulation-trained":[152],"on":[154],"hardware":[156],"long-horizon,":[159],"multi-stage":[160],"manipulation":[161],"task.":[162],"Website":[163],"code:":[165],"diffusion-ppo.github.io":[166]},"counts_by_year":[{"year":2026,"cited_by_count":124},{"year":2025,"cited_by_count":85},{"year":2024,"cited_by_count":12}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-09-29T00:00:00"}