{"id":"https://openalex.org/W2903013229","doi":"https://doi.org/10.29007/6jsv","title":"What if the World Were Different? Gradient-Based Exploration for New Optimal Policies","display_name":"What if the World Were Different? Gradient-Based Exploration for New Optimal Policies","publication_year":2018,"publication_date":"2018-09-17","ids":{"openalex":"https://openalex.org/W2903013229","doi":"https://doi.org/10.29007/6jsv","mag":"2903013229"},"language":"en","primary_location":{"id":"doi:10.29007/6jsv","is_oa":true,"landing_page_url":"https://doi.org/10.29007/6jsv","pdf_url":"https://easychair.org/publications/open/m8H9","source":{"id":"https://openalex.org/S4220651395","display_name":"EPiC series in computing","issn_l":"2398-7340","issn":["2398-7340"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EPiC Series in Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://easychair.org/publications/open/m8H9","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100452078","display_name":"Rui Silva","orcid":"https://orcid.org/0000-0002-8200-9951"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]},{"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":["PT","US"],"is_corresponding":false,"raw_author_name":"Rui Silva","raw_affiliation_strings":["Computer Science Department, Carnegie Mellon University, Pittsburgh PA, USA","INESC-ID / Instituto Superior Tcnico, Universidade de Lisboa, Portugal","INESC-ID / Instituto Superior T\u00e9cnico, Universidade de Lisboa, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Carnegie Mellon University, Pittsburgh PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"INESC-ID / Instituto Superior Tcnico, Universidade de Lisboa, Portugal","institution_ids":["https://openalex.org/I121345201"]},{"raw_affiliation_string":"INESC-ID / Instituto Superior T\u00e9cnico, Universidade de Lisboa, Portugal","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I141596103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101616573","display_name":"Francisco S. Melo","orcid":"https://orcid.org/0000-0001-5705-7372"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Francisco S. Melo","raw_affiliation_strings":["INESC-ID / Instituto Superior Tcnico, Universidade de Lisboa, Portugal","INESC-ID / Instituto Superior T\u00e9cnico, Universidade de Lisboa, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INESC-ID / Instituto Superior Tcnico, Universidade de Lisboa, Portugal","institution_ids":["https://openalex.org/I121345201"]},{"raw_affiliation_string":"INESC-ID / Instituto Superior T\u00e9cnico, Universidade de Lisboa, Portugal","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I141596103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088276691","display_name":"Manuela Veloso","orcid":"https://orcid.org/0000-0001-6738-238X"},"institutions":[{"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":"Manuela Veloso","raw_affiliation_strings":["Machine Learning Department, Carnegie Mellon University, Pittsburgh PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Department, Carnegie Mellon University, Pittsburgh PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"55","issue":null,"first_page":"229","last_page":"214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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":0.9983999729156494,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9657999873161316,"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":0.9602000117301941,"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/computer-science","display_name":"Computer science","score":0.6869156360626221},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6375269889831543},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5896072387695312},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5869778990745544},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5302255749702454},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5091492533683777},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4987795352935791},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4209798574447632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25050950050354004},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1430254876613617},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12368899583816528}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6869156360626221},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6375269889831543},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5896072387695312},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5869778990745544},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5302255749702454},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5091492533683777},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4987795352935791},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4209798574447632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25050950050354004},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1430254876613617},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12368899583816528},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.29007/6jsv","is_oa":true,"landing_page_url":"https://doi.org/10.29007/6jsv","pdf_url":"https://easychair.org/publications/open/m8H9","source":{"id":"https://openalex.org/S4220651395","display_name":"EPiC series in computing","issn_l":"2398-7340","issn":["2398-7340"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EPiC Series in Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.29007/6jsv","is_oa":true,"landing_page_url":"https://doi.org/10.29007/6jsv","pdf_url":"https://easychair.org/publications/open/m8H9","source":{"id":"https://openalex.org/S4220651395","display_name":"EPiC series in computing","issn_l":"2398-7340","issn":["2398-7340"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EPiC Series in Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G309696157","display_name":null,"funder_award_id":"UID/CEC/50021/2013","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320319180","display_name":"Carnegie Mellon Portugal","ror":null},{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"},{"id":"https://openalex.org/F4320335191","display_name":"Centro de Matem\u00e1tica Universidade do Porto","ror":"https://ror.org/043pwc612"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2903013229.pdf","grobid_xml":"https://content.openalex.org/works/W2903013229.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W186811004","https://openalex.org/W1485735559","https://openalex.org/W1514031120","https://openalex.org/W1626155273","https://openalex.org/W1927741686","https://openalex.org/W1944484981","https://openalex.org/W1988217924","https://openalex.org/W2023862787","https://openalex.org/W2036931518","https://openalex.org/W2116442740","https://openalex.org/W2119567691","https://openalex.org/W2121517924","https://openalex.org/W2140801763","https://openalex.org/W2145495721","https://openalex.org/W2161103575","https://openalex.org/W2294623867","https://openalex.org/W2294997557","https://openalex.org/W2303345904","https://openalex.org/W2395585410","https://openalex.org/W2576126396","https://openalex.org/W2773749769","https://openalex.org/W2950989964","https://openalex.org/W2963035419","https://openalex.org/W4230837952","https://openalex.org/W4232464577","https://openalex.org/W4298023569","https://openalex.org/W6639667798","https://openalex.org/W6640260801","https://openalex.org/W6640616608","https://openalex.org/W6648664037","https://openalex.org/W6680971464","https://openalex.org/W6697328684","https://openalex.org/W6751495484"],"related_works":["https://openalex.org/W2943623134","https://openalex.org/W2494523064","https://openalex.org/W2588219639","https://openalex.org/W2215759665","https://openalex.org/W2030292806","https://openalex.org/W2960358116","https://openalex.org/W4287727129","https://openalex.org/W3041172967","https://openalex.org/W2749065928","https://openalex.org/W2147155098"],"abstract_inverted_index":{"Planning":[0],"under":[1],"uncertainty":[2],"assumes":[3],"a":[4,34,54,169,176],"model":[5],"of":[6,14,17,22,24,43,77,81,86,109,119,151,155,189,195],"the":[7,11,15,25,41,46,63,75,78,87,95,106,110,117,137,142,149,153,156,160,187],"world":[8,64,88,138,157],"that":[9,36,45,62,93,102,132,148,158],"specifies":[10],"probabilistic":[12],"effects":[13],"actions":[16],"an":[18,130],"agent":[19,47,96],"in":[20,50,68,192],"terms":[21],"changes":[23,135],"state.":[26],"Given":[27],"such":[28],"model,":[29],"planning":[30,120],"proceeds":[31],"to":[32,52,136,141],"determine":[33],"policy":[35,108,164],"defines":[37],"for":[38,179],"each":[39],"state":[40],"choice":[42],"action":[44],"should":[48],"follow":[49],"order":[51],"maximize":[53],"reward":[55,100],"function.":[56],"In":[57],"this":[58,181],"work,":[59],"we":[60,174],"realize":[61],"can":[65,165],"be":[66,166],"changed":[67],"more":[69,99],"ways":[70],"than":[71,101],"those":[72],"possible":[73,103,125],"by":[74,104],"execution":[76],"agent\u2019s":[79],"repertoire":[80],"actions.":[82],"These":[83],"additional":[84,124],"configurations":[85],"may":[89],"allow":[90],"new":[91],"policies":[92],"let":[94],"accumulate":[97],"even":[98],"following":[105],"optimal":[107,163],"original":[111],"world.":[112],"We":[113,127],"introduce":[114],"and":[115,146],"formalize":[116],"problem":[118,150],"while":[121],"considering":[122],"these":[123],"worlds.":[126],"then":[128],"present":[129],"approach":[131,191],"models":[133],"feasible":[134],"as":[139,168],"modifications":[140],"probability":[143],"transition":[144],"function,":[145],"show":[147],"computing":[152],"configuration":[154],"allows":[159],"most":[161],"rewarding":[162],"formulated":[167],"constrained":[170],"optimization":[171,182],"problem.":[172,183],"Finally,":[173],"contribute":[175],"gradient-based":[177],"algorithm":[178],"solving":[180],"Experimental":[184],"evaluation":[185],"shows":[186],"effectiveness":[188],"our":[190],"multiple":[193],"problems":[194],"practical":[196],"interest.":[197]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
