{"id":"https://openalex.org/W4382465352","doi":"https://doi.org/10.1609/aaai.v37i7.25951","title":"Improving Long-Horizon Imitation through Instruction Prediction","display_name":"Improving Long-Horizon Imitation through Instruction Prediction","publication_year":2023,"publication_date":"2023-06-26","ids":{"openalex":"https://openalex.org/W4382465352","doi":"https://doi.org/10.1609/aaai.v37i7.25951"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v37i7.25951","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/25951/25723","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},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/25951/25723","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014139284","display_name":"Joey Hejna","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joey Hejna","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049349154","display_name":"Pieter Abbeel","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":"Pieter Abbeel","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103895643","display_name":"Lerrel Pinto","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lerrel Pinto","raw_affiliation_strings":["New York University"],"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":67},"biblio":{"volume":"37","issue":"7","first_page":"7857","last_page":"7865"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9971,"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/T10028","display_name":"Topic Modeling","score":0.9971,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9941,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9901,"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/abstraction","display_name":"Abstraction","score":0.44325185},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41098943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7944625},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.58171827},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.546229},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5251324},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.49453065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48120335},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.44325185},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41098943},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2995869},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v37i7.25951","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/25951/25723","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},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2306.12554","pdf_url":"https://arxiv.org/pdf/2306.12554","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v37i7.25951","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/25951/25723","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},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.7}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":52,"referenced_works":["https://openalex.org/W1931877416","https://openalex.org/W2168359464","https://openalex.org/W2620290674","https://openalex.org/W2636355936","https://openalex.org/W2771075179","https://openalex.org/W2780057514","https://openalex.org/W2805984364","https://openalex.org/W2890809352","https://openalex.org/W2897513296","https://openalex.org/W2903172725","https://openalex.org/W2907502844","https://openalex.org/W2914112028","https://openalex.org/W2918241733","https://openalex.org/W2947182319","https://openalex.org/W2949059942","https://openalex.org/W2950872548","https://openalex.org/W2951725892","https://openalex.org/W2963281204","https://openalex.org/W2963477323","https://openalex.org/W2963800628","https://openalex.org/W2980433389","https://openalex.org/W2995983596","https://openalex.org/W3001133964","https://openalex.org/W3004691725","https://openalex.org/W3027086341","https://openalex.org/W3034758614","https://openalex.org/W3094502228","https://openalex.org/W3098201885","https://openalex.org/W3109085430","https://openalex.org/W3115293622","https://openalex.org/W3122267274","https://openalex.org/W3125498464","https://openalex.org/W3126325318","https://openalex.org/W3126503612","https://openalex.org/W3167645943","https://openalex.org/W3169291081","https://openalex.org/W3176362845","https://openalex.org/W3176974620","https://openalex.org/W3201446109","https://openalex.org/W3203511201","https://openalex.org/W4214700710","https://openalex.org/W4286989192","https://openalex.org/W4287278739","https://openalex.org/W4287667696","https://openalex.org/W4287724327","https://openalex.org/W4288090575","https://openalex.org/W4288320194","https://openalex.org/W4288333712","https://openalex.org/W4288420089","https://openalex.org/W4297669644","https://openalex.org/W4297798492","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4313163053","https://openalex.org/W4300973204","https://openalex.org/W4253593777","https://openalex.org/W3162204513","https://openalex.org/W3045811229","https://openalex.org/W2382521049","https://openalex.org/W2165950148","https://openalex.org/W2144385241","https://openalex.org/W2045155990","https://openalex.org/W1585007175"],"abstract_inverted_index":{"Complex,":[0],"long-horizon":[1],"planning":[2,87],"and":[3,27,100,133],"its":[4],"combinatorial":[5],"nature":[6],"pose":[7],"steep":[8],"challenges":[9],"for":[10,114],"learning-based":[11],"agents.":[12],"Difficulties":[13],"in":[14,19,52,86,125],"such":[15],"settings":[16],"are":[17],"exacerbated":[18],"low":[20],"data":[21],"regimes":[22],"where":[23],"over-fitting":[24],"stifles":[25],"generalization":[26],"compounding":[28],"errors":[29],"hurt":[30],"accuracy.":[31],"In":[32,103],"this":[33],"work,":[34],"we":[35,55,78,106],"explore":[36],"the":[37,98],"use":[38],"of":[39,44,75,95],"an":[40,59],"often":[41],"unused":[42],"source":[43],"auxiliary":[45],"supervision:":[46],"language.":[47],"Inspired":[48],"by":[49],"recent":[50],"advances":[51],"transformer-based":[53],"models,":[54],"train":[56],"agents":[57],"with":[58,91],"instruction":[60,81,109],"prediction":[61],"loss":[62],"that":[63,69,80,108,116,127],"encourages":[64],"learning":[65],"temporally":[66],"extended":[67],"representations":[68],"operate":[70],"at":[71,138],"a":[72,92],"high":[73],"level":[74],"abstraction.":[76],"Concretely,":[77],"demonstrate":[79],"modeling":[82,110],"significantly":[83],"improves":[84],"performance":[85],"environments":[88,126],"when":[89],"training":[90],"limited":[93],"number":[94],"demonstrations":[96],"on":[97],"BabyAI":[99],"Crafter":[101],"benchmarks.":[102],"further":[104],"analysis":[105],"find":[107],"is":[111],"most":[112],"important":[113],"tasks":[115],"require":[117,128],"complex":[118],"reasoning,":[119],"while":[120],"understandably":[121],"offering":[122],"smaller":[123],"gains":[124],"simple":[129],"plans.":[130],"More":[131],"details":[132],"code":[134],"can":[135],"be":[136],"found":[137],"\\url{https://github.com/jhejna/instruction-prediction}.":[139]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4382465352","counts_by_year":[],"updated_date":"2025-01-02T19:04:11.707859","created_date":"2023-06-29"}