{"id":"https://openalex.org/W3034528880","doi":"https://doi.org/10.24963/ijcai.2020/280","title":"IR-VIC: Unsupervised Discovery of Sub-goals for Transfer in RL","display_name":"IR-VIC: Unsupervised Discovery of Sub-goals for Transfer in RL","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3034528880","doi":"https://doi.org/10.24963/ijcai.2020/280","mag":"3034528880"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/280","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/280","pdf_url":"https://www.ijcai.org/proceedings/2020/0280.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0280.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054644876","display_name":"Nirbhay Modhe","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nirbhay Modhe","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029904363","display_name":"Prithvijit Chattopadhyay","orcid":"https://orcid.org/0000-0001-7555-3644"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prithvijit Chattopadhyay","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102792137","display_name":"Mohit Sharma","orcid":"https://orcid.org/0000-0002-5680-9111"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohit Sharma","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102972112","display_name":"Abhishek Das","orcid":"https://orcid.org/0000-0002-4718-4316"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Das","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050342343","display_name":"Devi Parikh","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Devi Parikh","raw_affiliation_strings":["Facebook AI Research","Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014035752","display_name":"Dhruv Batra","orcid":"https://orcid.org/0000-0002-1358-0011"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Dhruv Batra","raw_affiliation_strings":["Facebook AI Research","Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041797310","display_name":"Ramakrishna Vedantam","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ramakrishna Vedantam","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2022","last_page":"2028"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9970999956130981,"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":0.9970999956130981,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9940999746322632,"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":0.9904999732971191,"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/observability","display_name":"Observability","score":0.9131646156311035},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.6826984882354736},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6599517464637756},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5420836210250854},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5290911197662354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46805140376091003},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4492902159690857},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4237118363380432},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1964271366596222}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.9131646156311035},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.6826984882354736},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6599517464637756},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5420836210250854},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5290911197662354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46805140376091003},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4492902159690857},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4237118363380432},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1964271366596222},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2020/280","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/280","pdf_url":"https://www.ijcai.org/proceedings/2020/0280.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.10580","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.10580","pdf_url":"https://arxiv.org/pdf/1907.10580","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":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/280","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/280","pdf_url":"https://www.ijcai.org/proceedings/2020/0280.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034528880.pdf","grobid_xml":"https://content.openalex.org/works/W3034528880.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W187288179","https://openalex.org/W285471286","https://openalex.org/W1686946872","https://openalex.org/W1786044565","https://openalex.org/W1970302770","https://openalex.org/W2098774185","https://openalex.org/W2099111195","https://openalex.org/W2115807451","https://openalex.org/W2117533361","https://openalex.org/W2143435603","https://openalex.org/W2160589914","https://openalex.org/W2173248099","https://openalex.org/W2398870399","https://openalex.org/W2556477470","https://openalex.org/W2592215206","https://openalex.org/W2735995851","https://openalex.org/W2753738274","https://openalex.org/W2882987577","https://openalex.org/W2883433335","https://openalex.org/W2886000153","https://openalex.org/W2913854057","https://openalex.org/W2950040888","https://openalex.org/W2950152428","https://openalex.org/W2963199420","https://openalex.org/W2963343988","https://openalex.org/W2963438456","https://openalex.org/W2963523627","https://openalex.org/W2963864421","https://openalex.org/W2964009285","https://openalex.org/W2964160479","https://openalex.org/W4293469690"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2765830098","https://openalex.org/W2967463586","https://openalex.org/W2074679142","https://openalex.org/W1971989957","https://openalex.org/W2607437843","https://openalex.org/W4295700147","https://openalex.org/W2963162727","https://openalex.org/W2106714532","https://openalex.org/W4297979791"],"abstract_inverted_index":{"We":[0,19],"propose":[1],"a":[2,38],"novel":[3],"framework":[4,25],"to":[5,35,46,82],"identify":[6,47],"sub-goals":[7,48,69],"useful":[8],"for":[9],"exploration":[10,72],"in":[11,85],"sequential":[12],"decision":[13],"making":[14],"tasks":[15,80],"under":[16],"partial":[17],"observability.":[18],"utilize":[20],"the":[21,33],"variational":[22],"intrinsic":[23],"control":[24],"(Gregor":[26],"et.al.,":[27],"2016)":[28],"which":[29],"maximizes":[30],"empowerment":[31],"--":[32],"ability":[34],"reliably":[36],"reach":[37],"diverse":[39],"set":[40],"of":[41],"states":[42,50],"and":[43,73],"show":[44],"how":[45],"as":[49],"with":[51],"high":[52],"necessary":[53],"option":[54],"information":[55,58],"through":[56],"an":[57],"theoretic":[59],"regularizer.":[60],"Despite":[61],"being":[62],"discovered":[63],"without":[64],"explicit":[65],"goal":[66],"supervision,":[67],"our":[68],"provide":[70],"better":[71],"sample":[74],"complexity":[75],"on":[76],"challenging":[77],"grid-world":[78],"navigation":[79],"compared":[81],"supervised":[83],"counterparts":[84],"prior":[86],"work.":[87]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}