{"id":"https://openalex.org/W2258731934","doi":"https://doi.org/10.24963/ijcai.2017/700","title":"Value Iteration Networks","display_name":"Value Iteration Networks","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2258731934","doi":"https://doi.org/10.24963/ijcai.2017/700","mag":"2258731934"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/700","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/700","pdf_url":"https://www.ijcai.org/proceedings/2017/0700.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0700.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020699288","display_name":"Aviv Tamar","orcid":"https://orcid.org/0000-0002-1972-854X"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aviv Tamar","raw_affiliation_strings":["UC Berkeley","UC Berkeley#TAB#"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley#TAB#","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101458171","display_name":"Yi Wu","orcid":"https://orcid.org/0000-0003-3838-7418"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Wu","raw_affiliation_strings":["UC Berkeley","UC Berkeley#TAB#"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley#TAB#","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111978170","display_name":"Garrett Thomas","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Garrett Thomas","raw_affiliation_strings":["UC Berkeley","UC Berkeley#TAB#"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley#TAB#","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Levine","raw_affiliation_strings":["UC Berkeley","UC Berkeley#TAB#"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley#TAB#","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049349154","display_name":"Pieter Abbeel","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I4210161460","display_name":"OpenAI (United States)","ror":"https://ror.org/05wx9n238","country_code":"US","type":"company","lineage":["https://openalex.org/I4210161460"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pieter Abbeel","raw_affiliation_strings":["OpenAI","UC Berkeley","UC Berkeley and OpenAI#TAB#"],"affiliations":[{"raw_affiliation_string":"OpenAI","institution_ids":["https://openalex.org/I4210161460"]},{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley and OpenAI#TAB#","institution_ids":["https://openalex.org/I4210161460","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5020699288"],"corresponding_institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":37.415,"has_fulltext":false,"cited_by_count":228,"citation_normalized_percentile":{"value":0.99771597,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"4949","last_page":"4953"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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":0.9976000189781189,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9937999844551086,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9768000245094299,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.743138313293457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7235510349273682},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5848323106765747},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5821881294250488},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5733441114425659},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5550906658172607},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5374966263771057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5374959111213684},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.5309635400772095},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4929194450378418},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.43582579493522644},{"id":"https://openalex.org/keywords/value-network","display_name":"Value network","score":0.41955411434173584},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41664111614227295},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3489115834236145},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3464212417602539},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2640281915664673},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15349140763282776}],"concepts":[{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.743138313293457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7235510349273682},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5848323106765747},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5821881294250488},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5733441114425659},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5550906658172607},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5374966263771057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5374959111213684},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.5309635400772095},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4929194450378418},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.43582579493522644},{"id":"https://openalex.org/C89249532","wikidata":"https://www.wikidata.org/wiki/Q7912758","display_name":"Value network","level":3,"score":0.41955411434173584},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41664111614227295},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3489115834236145},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3464212417602539},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2640281915664673},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15349140763282776},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C4216890","wikidata":"https://www.wikidata.org/wiki/Q815823","display_name":"Business model","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.24963/ijcai.2017/700","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/700","pdf_url":"https://www.ijcai.org/proceedings/2017/0700.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1602.02867","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1602.02867","pdf_url":"https://arxiv.org/pdf/1602.02867","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2258731934","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1602.02867","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1602.02867","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1602.02867","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-journal"},{"id":"mag:2964077562","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1602.02867","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":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/700","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/700","pdf_url":"https://www.ijcai.org/proceedings/2017/0700.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1171700966","display_name":null,"funder_award_id":"NSF CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2273398380","display_name":null,"funder_award_id":"NSF CAREER","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G2992220136","display_name":"CAREER: Apprenticeship Learning for Robotic Manipulation of Deformable Objects","funder_award_id":"1351028","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5524522455","display_name":null,"funder_award_id":"DARPA","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6724302884","display_name":null,"funder_award_id":"FA8750-14-C-0011","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7480437923","display_name":null,"funder_award_id":"PPAML","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8211109110","display_name":null,"funder_award_id":"PECASE","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8434508126","display_name":null,"funder_award_id":"#1351028","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G859713086","display_name":null,"funder_award_id":"PECASE","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2258731934.pdf","grobid_xml":"https://content.openalex.org/works/W2258731934.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W1514535095","https://openalex.org/W1606347560","https://openalex.org/W1777239053","https://openalex.org/W1903029394","https://openalex.org/W1983364832","https://openalex.org/W1999874108","https://openalex.org/W2013614847","https://openalex.org/W2021128738","https://openalex.org/W2022508996","https://openalex.org/W2084920657","https://openalex.org/W2098774185","https://openalex.org/W2101926813","https://openalex.org/W2104171826","https://openalex.org/W2105960367","https://openalex.org/W2112796928","https://openalex.org/W2116442740","https://openalex.org/W2117675763","https://openalex.org/W2121103318","https://openalex.org/W2121863487","https://openalex.org/W2123491406","https://openalex.org/W2135639338","https://openalex.org/W2136064009","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2151210636","https://openalex.org/W2158782408","https://openalex.org/W2164424353","https://openalex.org/W2167590754","https://openalex.org/W2169498096","https://openalex.org/W2175344611","https://openalex.org/W2260756217","https://openalex.org/W2296673577","https://openalex.org/W2341171179","https://openalex.org/W2342662072","https://openalex.org/W2407125866","https://openalex.org/W2507756961","https://openalex.org/W2911273949","https://openalex.org/W2949190276","https://openalex.org/W2949248709","https://openalex.org/W2949608212","https://openalex.org/W2950527759","https://openalex.org/W2952840881","https://openalex.org/W2962957031","https://openalex.org/W2963430173","https://openalex.org/W2963825768","https://openalex.org/W2964161785"],"related_works":["https://openalex.org/W2964043796","https://openalex.org/W2257979135","https://openalex.org/W2145339207","https://openalex.org/W2173248099","https://openalex.org/W2121863487","https://openalex.org/W1757796397","https://openalex.org/W2964161785","https://openalex.org/W2194775991","https://openalex.org/W2951660448","https://openalex.org/W2949608212","https://openalex.org/W2736601468","https://openalex.org/W2964220198","https://openalex.org/W2119717200","https://openalex.org/W2064675550","https://openalex.org/W2950872548","https://openalex.org/W1522301498","https://openalex.org/W2766447205","https://openalex.org/W2098774185","https://openalex.org/W2140135625","https://openalex.org/W2109910161"],"abstract_inverted_index":{"We":[0,84],"introduce":[1],"the":[2,49,112,118],"value":[3],"iteration":[4],"network":[5,11],"(VIN):":[6],"a":[7,13,44,57,79,103],"fully":[8],"differentiable":[9,46],"neural":[10,59],"with":[12,117],"`planning":[14],"module'":[15],"embedded":[16],"within.":[17],"VINs":[18],"can":[19,53],"learn":[20],"to":[21,40,97],"plan,":[22],"and":[23,61,73,77,106],"are":[24],"suitable":[25],"for":[26,36],"predicting":[27],"outcomes":[28],"that":[29,86],"involve":[30],"planning-based":[31],"reasoning,":[32],"such":[33],"as":[34,56],"policies":[35,70,94],"reinforcement":[37],"learning.":[38],"Key":[39],"our":[41],"approach":[42],"is":[43,102],"novel":[45],"approximation":[47],"of":[48,111],"value-iteration":[50],"algorithm,":[51],"which":[52],"be":[54],"represented":[55],"convolutional":[58],"network,":[60],"trained":[62],"end-to-end":[63],"using":[64],"standard":[65],"backpropagation.We":[66],"evaluate":[67],"VIN":[68,93],"based":[69,81],"on":[71,78],"discrete":[72],"continuous":[74],"path-planning":[75],"domains,":[76],"natural-language":[80],"search":[82],"task.":[83],"show":[85],"by":[87],"learning":[88],"an":[89],"explicit":[90],"planning":[91],"computation,":[92],"generalize":[95],"better":[96],"new,":[98],"unseen":[99],"domains.This":[100],"paper":[101,116],"significantly":[104],"abridged":[105],"IJCAI":[107],"audience":[108],"targeted":[109],"version":[110],"original":[113],"NIPS":[114],"2016":[115],"same":[119],"title,":[120],"available":[121],"here:":[122],"https://arxiv.org/abs/1602.02867":[123]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":35},{"year":2020,"cited_by_count":48},{"year":2019,"cited_by_count":50},{"year":2018,"cited_by_count":49},{"year":2017,"cited_by_count":33},{"year":2016,"cited_by_count":7}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}