{"id":"https://openalex.org/W4367016730","doi":"https://doi.org/10.1109/tac.2023.3270060","title":"Parallel and Flexible Dynamic Programming via the Mini-Batch Bellman Operator","display_name":"Parallel and Flexible Dynamic Programming via the Mini-Batch Bellman Operator","publication_year":2023,"publication_date":"2023-04-25","ids":{"openalex":"https://openalex.org/W4367016730","doi":"https://doi.org/10.1109/tac.2023.3270060"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2023.3270060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2023.3270060","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11850/616836","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091908459","display_name":"Matilde Gargiani","orcid":"https://orcid.org/0000-0001-8615-6214"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Matilde Gargiani","raw_affiliation_strings":["Automatic Control Laboratory ETH, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-8615-6214","affiliations":[{"raw_affiliation_string":"Automatic Control Laboratory ETH, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011462733","display_name":"Andrea Martinelli","orcid":"https://orcid.org/0000-0003-3206-9814"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andrea Martinelli","raw_affiliation_strings":["Automatic Control Laboratory ETH, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-3206-9814","affiliations":[{"raw_affiliation_string":"Automatic Control Laboratory ETH, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086798183","display_name":"Max Ruts Martinez","orcid":"https://orcid.org/0009-0001-4295-8490"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Max Ruts Martinez","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0009-0001-4295-8490","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007359599","display_name":"John Lygeros","orcid":"https://orcid.org/0000-0002-6159-1962"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"John Lygeros","raw_affiliation_strings":["Automatic Control Laboratory ETH, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-6159-1962","affiliations":[{"raw_affiliation_string":"Automatic Control Laboratory ETH, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6526,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73796856,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"69","issue":"1","first_page":"455","last_page":"462"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.7527405023574829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.591346025466919},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5455065369606018},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4962330460548401},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.4763869643211365},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4323032796382904},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42809659242630005},{"id":"https://openalex.org/keywords/multiplication-operator","display_name":"Multiplication operator","score":0.42307180166244507},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3303268849849701},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3082134425640106},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.07099369168281555}],"concepts":[{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.7527405023574829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.591346025466919},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5455065369606018},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4962330460548401},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4763869643211365},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4323032796382904},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42809659242630005},{"id":"https://openalex.org/C82916341","wikidata":"https://www.wikidata.org/wiki/Q6934990","display_name":"Multiplication operator","level":3,"score":0.42307180166244507},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3303268849849701},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3082134425640106},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.07099369168281555},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tac.2023.3270060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2023.3270060","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-article"},{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/616836","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/616836","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Automatic Control, 69 (1)","raw_type":"info:eu-repo/semantics/acceptedVersion"},{"id":"doi:10.3929/ethz-b-000616836","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-b-000616836","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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-journal"}],"best_oa_location":{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/616836","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/616836","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Automatic Control, 69 (1)","raw_type":"info:eu-repo/semantics/acceptedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G6421654716","display_name":null,"funder_award_id":"787845","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"}],"funders":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2001770658","https://openalex.org/W2023901033","https://openalex.org/W2038497950","https://openalex.org/W2056653303","https://openalex.org/W2115091574","https://openalex.org/W2117686388","https://openalex.org/W2121517924","https://openalex.org/W2154834860","https://openalex.org/W2167489871","https://openalex.org/W2963433607","https://openalex.org/W2992727511","https://openalex.org/W3141650078","https://openalex.org/W3216251000","https://openalex.org/W4206097460","https://openalex.org/W4214717370","https://openalex.org/W4285292047","https://openalex.org/W4295312788","https://openalex.org/W4388917629","https://openalex.org/W6638704708","https://openalex.org/W6766978945","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2046459711","https://openalex.org/W4288636821","https://openalex.org/W2092836648","https://openalex.org/W2083593758","https://openalex.org/W2649360600","https://openalex.org/W2970750770","https://openalex.org/W2953390772","https://openalex.org/W2147250289","https://openalex.org/W2391621545","https://openalex.org/W2909975239"],"abstract_inverted_index":{"The":[0,49],"Bellman":[1,25,93,122],"operator":[2,26,61,85,114,150,176,210,229],"constitutes":[3],"the":[4,15,24,28,44,46,59,64,72,89,100,103,108,112,116,121,125,128,148,152,166,169,174,184,188,192,195,199,207,216,219,223,227,239],"foundation":[5],"of":[6,23,54,66,74,107,127,168,187,194,206,226,241,247],"dynamic":[7],"programming":[8],"(DP).":[9],"An":[10],"alternative":[11],"is":[12,139,211],"presented":[13],"by":[14,120],"Gauss\u2013Seidel":[16,60,113],"operator,":[17,130],"whose":[18],"evaluation,":[19],"differently":[20],"from":[21],"that":[22],"where":[27],"states":[29],"are":[30],"all":[31],"processed":[32],"at":[33,38,63,98],"once,":[34],"updates":[35],"one":[36,144,236],"state":[37],"a":[39,83,131],"time":[40],"while":[41],"incorporating":[42],"into":[43],"computation":[45],"interim":[47],"results.":[48],"provably":[50],"better":[51,104],"convergence":[52,105,167],"rate":[53,106],"DP":[55,154,170],"methods":[56,109],"based":[57,110,172],"on":[58,111,173,183,198],"comes":[62],"price":[65],"an":[67,202],"inherent":[68],"sequentiality,":[69],"which":[70,96,234],"prevents":[71],"exploitation":[73],"modern":[75],"multicore":[76],"systems.":[77],"In":[78,213],"this":[79],"work,":[80],"we":[81],"propose":[82],"new":[84,129,149,175,189],"for":[86,134],"DP,":[87],"namely,":[88],"<italic":[90],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[91],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">mini-batch":[92],"operator</i>":[94],",":[95],"aims":[97],"realizing":[99],"tradeoff":[101],"between":[102],"and":[115,160,191,230,249],"parallelization":[117],"capability":[118],"offered":[119],"operator.":[123],"After":[124],"introduction":[126],"theoretical":[132,217],"analysis":[133],"validating":[135],"its":[136,178,231,242],"fundamental":[137],"properties":[138,142],"conducted.":[140,212],"Such":[141],"allow":[143],"to":[145,237,244],"successfully":[146],"deploy":[147],"in":[151],"main":[153],"schemes,":[155],"such":[156],"as":[157],"value":[158],"iteration":[159],"modified":[161],"policy":[162],"iteration.":[163],"We":[164],"compare":[165],"algorithm":[171],"with":[177,215],"earlier":[179],"counterparts,":[180],"shedding":[181],"light":[182],"algorithmic":[185],"advantages":[186],"formulation":[190],"impact":[193],"batch-size":[196],"parameter":[197],"convergence.":[200],"Finally,":[201],"extensive":[203],"numerical":[204,220],"evaluation":[205],"newly":[208],"introduced":[209],"accordance":[214],"derivations,":[218],"results":[221],"show":[222],"competitive":[224],"performance":[225],"proposed":[228],"superior":[232],"flexibility,":[233],"allows":[235],"adapt":[238],"efficiency":[240],"iterations":[243],"different":[245],"structures":[246],"MDPs":[248],"hardware":[250],"setups.":[251]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
