{"id":"https://openalex.org/W2904784373","doi":"https://doi.org/10.1609/aaai.v33i01.33017530","title":"Deep Reactive Policies for Planning in Stochastic Nonlinear Domains","display_name":"Deep Reactive Policies for Planning in Stochastic Nonlinear Domains","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2904784373","doi":"https://doi.org/10.1609/aaai.v33i01.33017530","mag":"2904784373"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33017530","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33017530","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4744/4622","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://ojs.aaai.org/index.php/AAAI/article/download/4744/4622","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079849725","display_name":"Thiago Pereira Bueno","orcid":"https://orcid.org/0000-0003-1999-9697"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thiago P. Bueno","raw_affiliation_strings":["University of S\u00e3o Paulo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070668357","display_name":"Leliane Nunes de Barros","orcid":"https://orcid.org/0000-0002-9128-0188"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Leliane N. De Barros","raw_affiliation_strings":["University of Sao Paulo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sao Paulo","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063271727","display_name":"Denis Deratani Mau\u00e1","orcid":"https://orcid.org/0000-0003-2297-6349"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Denis D. Mau\u00e1","raw_affiliation_strings":["University of Sao Paulo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sao Paulo","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028174137","display_name":"Scott Sanner","orcid":"https://orcid.org/0000-0001-7984-8394"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Scott Sanner","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"7530","last_page":"7537"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9970999956130981,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9970999956130981,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.995199978351593,"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/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/computer-science","display_name":"Computer science","score":0.6658686399459839},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5912026762962341},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5359312891960144},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5163092017173767},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.5065068006515503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43706756830215454},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.43394726514816284},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.4260692596435547},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4227103590965271},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.42064353823661804},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.2715373933315277},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15874242782592773},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.1412506103515625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6658686399459839},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5912026762962341},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5359312891960144},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5163092017173767},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.5065068006515503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43706756830215454},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.43394726514816284},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.4260692596435547},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4227103590965271},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42064353823661804},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.2715373933315277},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15874242782592773},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.1412506103515625},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33017530","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33017530","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4744/4622","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/4744","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4744","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.v33i01.33017530","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33017530","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4744/4622","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":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7300000190734863}],"awards":[{"id":"https://openalex.org/G1067875432","display_name":null,"funder_award_id":"2015/01587","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G158177532","display_name":null,"funder_award_id":"420669/2016-7","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G2699740938","display_name":null,"funder_award_id":"2016-5","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G4297708386","display_name":null,"funder_award_id":"308433/2014-9","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G4402799499","display_name":null,"funder_award_id":"2015/","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G6254690332","display_name":null,"funder_award_id":"303920/2016-5","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G7700111595","display_name":null,"funder_award_id":"2016-7","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G8279803501","display_name":null,"funder_award_id":"2015/01587-0","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"}],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"},{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2904784373.pdf","grobid_xml":"https://content.openalex.org/works/W2904784373.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W12755008","https://openalex.org/W1585773866","https://openalex.org/W1601380202","https://openalex.org/W1601974704","https://openalex.org/W1619459736","https://openalex.org/W1646152356","https://openalex.org/W1972440681","https://openalex.org/W2061504687","https://openalex.org/W2093233187","https://openalex.org/W2095996877","https://openalex.org/W2119567691","https://openalex.org/W2128459535","https://openalex.org/W2130942839","https://openalex.org/W2145339207","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2176412452","https://openalex.org/W2257979135","https://openalex.org/W2271840356","https://openalex.org/W2523246573","https://openalex.org/W2604173138","https://openalex.org/W2608848790","https://openalex.org/W2749952662","https://openalex.org/W2754596546","https://openalex.org/W2810623284","https://openalex.org/W2952726221","https://openalex.org/W2963058385","https://openalex.org/W2963285578","https://openalex.org/W2963548923","https://openalex.org/W4298684625","https://openalex.org/W4394666973","https://openalex.org/W6600494169","https://openalex.org/W6635991215","https://openalex.org/W6674334281","https://openalex.org/W6679436768","https://openalex.org/W7001894244"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W1734617322"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,21,45,63,80,114,211],"applying":[3],"deep":[4,100],"learning":[5,48],"to":[6,39,69,92,104,141,223],"planning":[7,108,152],"have":[8],"shown":[9],"that":[10,138,170],"Deep":[11],"Reactive":[12],"Policies":[13],"(DRPs)":[14],"can":[15,179],"be":[16,40,180],"powerful":[17],"for":[18,77,185],"fast":[19],"decision-making":[20],"complex":[22],"environments.":[23],"However,":[24],"an":[25,111],"important":[26],"limitation":[27],"of":[28,36,54,123,206,209,219,233],"current":[29],"DRP-based":[30],"approaches":[31],"is":[32,91,130,236],"either":[33],"the":[34,51,106,121,124,128,212,230],"need":[35],"optimal":[37],"planners":[38,228],"used":[41],"as":[42,98,110],"ground":[43],"truth":[44],"a":[46,75,95,99,115,204],"supervised":[47],"setting":[49],"or":[50],"sample":[52],"complexity":[53],"high-variance":[55],"policy":[56,86,97],"gradient":[57,135],"estimators,":[58],"which":[59],"are":[60,139],"particularly":[61],"troublesome":[62],"continuous":[64,81,176],"state-action":[65],"domains.":[66],"In":[67],"order":[68],"overcome":[70],"those":[71],"limitations,":[72],"we":[73,202],"introduce":[74],"framework":[76],"training":[78],"DRPs":[79,171,220],"stochastic":[82,116,151],"spaces":[83],"via":[84],"gradient-based":[85,227],"search.":[87],"The":[88],"general":[89],"approach":[90,149,184],"explicitly":[93],"encode":[94],"parametric":[96],"neural":[101],"network,":[102],"and":[103,159,166,191],"formulate":[105],"probabilistic":[107],"problem":[109],"optimization":[112,129],"task":[113],"computation":[117],"graph":[118],"by":[119,133,182],"exploiting":[120],"re-parameterization":[122],"transition":[125,158],"probability":[126],"densities;":[127],"then":[131],"solved":[132],"leveraging":[134],"descent":[136],"algorithms":[137],"able":[140],"handle":[142],"non-convex":[143],"objective":[144],"functions.":[145],"We":[146],"benchmark":[147],"our":[148,183],"against":[150],"domains":[153],"exhibiting":[154],"arbitrary":[155],"differentiable":[156],"nonlinear":[157],"cost":[160],"functions":[161],"(e.g.,":[162],"Reservoir":[163],"Control,":[164],"HVAC":[165],"Navigation).":[167],"Results":[168],"show":[169],"with":[172,187],"more":[173],"than":[174],"125,000":[175],"action":[177,193],"parameters":[178],"optimized":[181],"problems":[186],"30":[188,192],"state":[189],"fluents":[190,194],"on":[195],"inexpensive":[196],"hardware":[197],"under":[198],"6":[199],"minutes.":[200],"Also,":[201],"observed":[203],"speedup":[205],"5":[207],"orders":[208],"magnitude":[210],"average":[213],"inference":[214],"time":[215],"per":[216],"decision":[217],"step":[218],"when":[221,229],"compared":[222],"other":[224],"state-of-the-art":[225],"online":[226],"same":[231],"level":[232],"solution":[234],"quality":[235],"required.":[237]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}