{"id":"https://openalex.org/W2900902742","doi":"https://doi.org/10.1609/aaai.v33i01.33013151","title":"Model Learning for Look-Ahead Exploration in Continuous Control","display_name":"Model Learning for Look-Ahead Exploration in Continuous Control","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2900902742","doi":"https://doi.org/10.1609/aaai.v33i01.33013151","mag":"2900902742"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33013151","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013151","pdf_url":null,"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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v33i01.33013151","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103177535","display_name":"Arpit Agarwal","orcid":"https://orcid.org/0000-0002-1594-5264"},"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":"Arpit Agarwal","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040655097","display_name":"Katharina Muelling","orcid":null},"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":"Katharina Muelling","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008661738","display_name":"Katerina Fragkiadaki","orcid":null},"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":"Katerina Fragkiadaki","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"3151","last_page":"3158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9896000027656555,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/chaining","display_name":"Chaining","score":0.8160876631736755},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7408963441848755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7186610698699951},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.6267892122268677},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5644902586936951},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5221964716911316},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.48280107975006104},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4804691672325134},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.4177606403827667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4022024869918823},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28036099672317505},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11355376243591309}],"concepts":[{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.8160876631736755},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7408963441848755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7186610698699951},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.6267892122268677},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5644902586936951},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5221964716911316},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.48280107975006104},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4804691672325134},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.4177606403827667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4022024869918823},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28036099672317505},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11355376243591309},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1609/aaai.v33i01.33013151","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013151","pdf_url":null,"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:arXiv.org:1811.08086","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.08086","pdf_url":"https://arxiv.org/pdf/1811.08086","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:2900902742","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1811.08086","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.1811.08086","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.08086","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":"Preprint"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33013151","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013151","pdf_url":null,"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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W567721252","https://openalex.org/W1585013689","https://openalex.org/W1691728462","https://openalex.org/W1980035368","https://openalex.org/W2028678875","https://openalex.org/W2109910161","https://openalex.org/W2110322955","https://openalex.org/W2118688707","https://openalex.org/W2121517924","https://openalex.org/W2132622533","https://openalex.org/W2139612737","https://openalex.org/W2151210636","https://openalex.org/W2158782408","https://openalex.org/W2160371091","https://openalex.org/W2173248099","https://openalex.org/W2174072647","https://openalex.org/W2181068523","https://openalex.org/W2253991908","https://openalex.org/W2256420211","https://openalex.org/W2280163991","https://openalex.org/W2335959470","https://openalex.org/W2419612459","https://openalex.org/W2473208550","https://openalex.org/W2498991332","https://openalex.org/W2592285981","https://openalex.org/W2604726708","https://openalex.org/W2614839826","https://openalex.org/W2623491082","https://openalex.org/W2733961795","https://openalex.org/W2743381431","https://openalex.org/W2766447205","https://openalex.org/W2788781499","https://openalex.org/W2795843265","https://openalex.org/W2949604932","https://openalex.org/W2951774643","https://openalex.org/W2951948137","https://openalex.org/W2962871243","https://openalex.org/W2962872206","https://openalex.org/W2963616477","https://openalex.org/W2964118020","https://openalex.org/W4211147054","https://openalex.org/W6616173779","https://openalex.org/W6635159692","https://openalex.org/W6637412569","https://openalex.org/W6676562469","https://openalex.org/W6683153233","https://openalex.org/W6683821272","https://openalex.org/W6685200453","https://openalex.org/W6692312642","https://openalex.org/W6695011786","https://openalex.org/W6740801417","https://openalex.org/W6745620495","https://openalex.org/W6750253780"],"related_works":["https://openalex.org/W2965662123","https://openalex.org/W3008744627","https://openalex.org/W3024199149","https://openalex.org/W3151079898","https://openalex.org/W3037443774","https://openalex.org/W3213301174","https://openalex.org/W2949243561","https://openalex.org/W3200054052","https://openalex.org/W2982795998","https://openalex.org/W3207864151","https://openalex.org/W3173031723","https://openalex.org/W2915039521","https://openalex.org/W3095548673","https://openalex.org/W3090658167","https://openalex.org/W3163571701","https://openalex.org/W3005607450","https://openalex.org/W3022124161","https://openalex.org/W3171051732","https://openalex.org/W3051139937","https://openalex.org/W2803281228"],"abstract_inverted_index":{"We":[0,101,147],"propose":[1],"an":[2],"exploration":[3,106,152],"method":[4],"that":[5,103,129,149,175],"incorporates":[6],"lookahead":[7,67],"search":[8,70],"over":[9,80],"basic":[10],"learnt":[11,61],"skills":[12,27,134,180],"and":[13,16,62,84,94,122,168],"their":[14],"dynamics,":[15,49],"use":[17,130,176],"it":[18],"for":[19],"reinforcement":[20],"learning":[21,111,157],"(RL)":[22],"of":[23,112,138,158,184],"manipulation":[24,114,160],"policies.":[25],"Our":[26],"are":[28,60,63],"multi-goal":[29],"policies":[30,88,115,126,161,172],"learned":[31],"in":[32,34,109,155],"isolation":[33],"simpler":[35],"environments":[36],"using":[37],"existing":[38],"multigoal":[39],"RL":[40,120,166],"formulations,":[41],"analogous":[42],"to":[43,124,144,170,190],"options":[44,131,177],"or":[45,132,178],"macroactions.":[46],"Coarse":[47],"skill":[48,58,99],"i.e.,":[50],"the":[51,86,104,139,150,185],"state":[52],"transition":[53],"caused":[54,96],"by":[55,97],"a":[56],"(complete)":[57],"execution,":[59],"unrolled":[64],"forward":[65],"during":[66,75],"search.":[68],"Policy":[69],"benefits":[71],"from":[72,92],"temporal":[73],"abstraction":[74],"exploration,":[76],"though":[77],"itself":[78],"operates":[79],"low-level":[81],"primitive":[82],"actions,":[83],"thus":[85],"resulting":[87],"does":[89],"not":[90],"suffer":[91],"suboptimality":[93],"inflexibility":[95],"coarse":[98],"chaining.":[100],"show":[102,148],"proposed":[105,151],"strategy":[107,153],"results":[108,154],"effective":[110,156],"complex":[113,159],"faster":[116,162],"than":[117,127,163,173],"current":[118,164],"state-of-the-art":[119,165],"methods,":[121,167],"converges":[123,169],"better":[125,171],"methods":[128,174],"parametrized":[133],"as":[135,142,181,188],"building":[136,182],"blocks":[137,183],"policy":[140,186],"itself,":[141,187],"opposed":[143,189],"guiding":[145,191],"exploration.":[146,192],"parameterized":[179]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}