{"id":"https://openalex.org/W2901310074","doi":"https://doi.org/10.48550/arxiv.1811.06889","title":"On the Complexity of Exploration in Goal-Driven Navigation","display_name":"On the Complexity of Exploration in Goal-Driven Navigation","publication_year":2018,"publication_date":"2018-11-16","ids":{"openalex":"https://openalex.org/W2901310074","doi":"https://doi.org/10.48550/arxiv.1811.06889","mag":"2901310074"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1811.06889","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.06889","pdf_url":"https://arxiv.org/pdf/1811.06889","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.06889","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008835202","display_name":"Maruan Al-Shedivat","orcid":"https://orcid.org/0000-0001-9037-1005","observed_orcids":["https://orcid.org/0000-0001-9037-1005"]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]},{"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":"Al-Shedivat, Maruan","raw_affiliation_strings":["Carnegie Mellon University , 2 Apple ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University , 2 Apple ,","institution_ids":["https://openalex.org/I4210153776","https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101529103","display_name":"Lisa Lee","orcid":"https://orcid.org/0000-0001-5058-9464","observed_orcids":["https://orcid.org/0000-0001-5058-9464"]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]},{"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":"Lee, Lisa","raw_affiliation_strings":["Carnegie Mellon University , 2 Apple ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University , 2 Apple ,","institution_ids":["https://openalex.org/I4210153776","https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071983998","display_name":"Ruslan Salakhutdinov","orcid":"https://orcid.org/0000-0002-3752-2756","observed_orcids":["https://orcid.org/0000-0002-3752-2756"]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]},{"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":"Salakhutdinov, Ruslan","raw_affiliation_strings":["Carnegie Mellon University , 2 Apple ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University , 2 Apple ,","institution_ids":["https://openalex.org/I4210153776","https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009547049","display_name":"Eric P. Xing","orcid":"https://orcid.org/0009-0005-9158-4201","observed_orcids":["https://orcid.org/0009-0005-9158-4201","https://orcid.org/0000-0002-3683-4280"]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]},{"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":"Xing, Eric","raw_affiliation_strings":["Carnegie Mellon University , 2 Apple ,","Petuum Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University , 2 Apple ,","institution_ids":["https://openalex.org/I4210153776","https://openalex.org/I74973139"]},{"raw_affiliation_string":"Petuum Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"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/T11574","display_name":"Artificial Intelligence in Games","score":9.999999747378752e-05,"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hierarchical-reinforcement-learning","display_name":"hierarchical reinforcement learning","score":0.8840000033378601},{"id":"https://openalex.org/keywords/first-passage-time","display_name":"first passage time","score":0.7860000133514404},{"id":"https://openalex.org/keywords/random-walks","display_name":"random walks","score":0.4749999940395355},{"id":"https://openalex.org/keywords/proximal-policy-optimization","display_name":"proximal policy optimization","score":0.7879999876022339},{"id":"https://openalex.org/keywords/sparse-rewards","display_name":"sparse rewards","score":0.5690000057220459},{"id":"https://openalex.org/keywords/procedural-content-generation","display_name":"procedural content generation","score":0.4300000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7567778825759888},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.6945238709449768},{"id":"https://openalex.org/C2780990831","wikidata":"https://www.wikidata.org/wiki/Q319141","display_name":"Conjecture","level":2,"score":0.5768569707870483},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5522437691688538},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4934007227420807},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48781874775886536},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.43023478984832764},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3373711109161377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2669943869113922},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17397597432136536},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.15108537673950195},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.08821380138397217},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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":3,"locations":[{"id":"pmh:oai:arXiv.org:1811.06889","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.06889","pdf_url":"https://arxiv.org/pdf/1811.06889","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2901310074","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1811.06889.pdf","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":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.1811.06889","doi":"https://doi.org/10.48550/arxiv.1811.06889","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.06889","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.06889","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.06889","pdf_url":"https://arxiv.org/pdf/1811.06889","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2901310074.pdf","grobid_xml":"https://content.openalex.org/works/W2901310074.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2109910161","https://openalex.org/W2145339207","https://openalex.org/W2335959470","https://openalex.org/W2523728418","https://openalex.org/W2552679343","https://openalex.org/W2553882142","https://openalex.org/W2623491082","https://openalex.org/W2724169821","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2964161785"],"related_works":["https://openalex.org/W4396598985","https://openalex.org/W4403578208","https://openalex.org/W3117161954","https://openalex.org/W2945263287","https://openalex.org/W4308245670","https://openalex.org/W7099161404","https://openalex.org/W7095520200","https://openalex.org/W2785780088","https://openalex.org/W2323085239","https://openalex.org/W7019241752"],"abstract_inverted_index":{"Building":[0],"agents":[1],"that":[2,148,167,180],"can":[3,30,77],"explore":[4],"their":[5],"environments":[6,68,173,182],"intelligently":[7],"is":[8,157],"a":[9,18,23,54,112,130,136],"challenging":[10],"open":[11],"problem.":[12],"In":[13],"this":[14],"paper,":[15],"we":[16,36,90,178],"make":[17],"step":[19],"towards":[20],"understanding":[21],"how":[22,46],"hierarchical":[24,137,189],"design":[25,37],"of":[26,56,83,96,111,132,139,161,186],"the":[27,41,50,81,94,104,116,162,168],"agent's":[28],"policy":[29,133],"affect":[31],"its":[32],"exploration":[33],"capabilities.":[34],"First,":[35],"EscapeRoom":[38],"environments,":[39],"where":[40],"agent":[42],"must":[43],"figure":[44],"out":[45],"to":[47,49,92,144],"navigate":[48],"exit":[51],"by":[52,80,99],"accomplishing":[53],"number":[55,82],"intermediate":[57],"tasks":[58],"(\\emph{subgoals}),":[59],"such":[60],"as":[61],"finding":[62],"keys":[63],"or":[64],"opening":[65],"doors.":[66],"Our":[67],"are":[69],"procedurally":[70],"generated":[71],"and":[72,85,106,127,135],"vary":[73],"in":[74,115,153],"complexity,":[75],"which":[76],"be":[78],"controlled":[79],"subgoals":[84],"relationships":[86],"between":[87,103],"them.":[88],"Next,":[89],"propose":[91],"measure":[93],"complexity":[95,187],"each":[97],"environment":[98,163],"constructing":[100],"dependency":[101,155],"graphs":[102,156],"goals":[105],"analytically":[107,149],"computing":[108],"\\emph{hitting":[109,151],"times}":[110],"random":[113],"walk":[114],"graph.":[117],"We":[118,146,165],"empirically":[119],"evaluate":[120],"Proximal":[121],"Policy":[122],"Optimization":[123],"(PPO)":[124],"with":[125],"sparse":[126],"shaped":[128],"rewards,":[129],"variation":[131],"sketches,":[134],"version":[138],"PPO":[140],"(called":[141],"HiPPO)":[142],"akin":[143],"h-DQN.":[145],"show":[147,179],"estimated":[150],"time}":[152],"goal":[154],"an":[158],"informative":[159],"metric":[160],"complexity.":[164],"conjecture":[166],"result":[169],"should":[170],"hold":[171],"for":[172],"other":[174],"than":[175],"navigation.":[176],"Finally,":[177],"solving":[181],"beyond":[183],"certain":[184],"level":[185],"requires":[188],"approaches.":[190]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2018-11-29T00:00:00"}