{"id":"https://openalex.org/W2963248502","doi":null,"title":"Unsupervised Discovery of Decision States for Transfer in Reinforcement Learning.","display_name":"Unsupervised Discovery of Decision States for Transfer in Reinforcement Learning.","publication_year":2019,"publication_date":"2019-07-24","ids":{"openalex":"https://openalex.org/W2963248502","mag":"2963248502"},"language":"en","primary_location":{"id":"mag:2963248502","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.10580.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},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.10580.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054644876","display_name":"Nirbhay Modhe","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nirbhay Modhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029904363","display_name":"Prithvijit Chattopadhyay","orcid":"https://orcid.org/0000-0001-7555-3644","observed_orcids":["https://orcid.org/0000-0001-7555-3644"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prithvijit Chattopadhyay","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7555-3644","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102792137","display_name":"Mohit Kumar Sharma","orcid":"https://orcid.org/0000-0002-5680-9111","observed_orcids":["https://orcid.org/0000-0002-5680-9111","https://orcid.org/0009-0006-6149-7411"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohit Sharma","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5680-9111","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102972112","display_name":"Abhishek Das","orcid":"https://orcid.org/0000-0002-4718-4316","observed_orcids":["https://orcid.org/0000-0002-4718-4316"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhishek Das","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4718-4316","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050342343","display_name":"Devi Parikh","orcid":"https://orcid.org/0000-0002-3779-6706","observed_orcids":["https://orcid.org/0000-0002-3779-6706"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Devi Parikh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014035752","display_name":"Dhruv Batra","orcid":"https://orcid.org/0000-0002-1358-0011","observed_orcids":["https://orcid.org/0000-0002-1358-0011"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dhruv Batra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041797310","display_name":"Ramakrishna Vedantam","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramakrishna Vedantam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":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/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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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":0.8709999918937683},{"id":"https://openalex.org/keywords/options-framework","display_name":"options framework","score":0.9290000200271606},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.7860000133514404},{"id":"https://openalex.org/keywords/information-bottleneck","display_name":"information bottleneck","score":0.9580000042915344},{"id":"https://openalex.org/keywords/mutual-information","display_name":"mutual information","score":0.8679999709129333},{"id":"https://openalex.org/keywords/exploration","display_name":"exploration","score":0.5770000219345093},{"id":"https://openalex.org/keywords/cross-domain-transfer","display_name":"cross-domain transfer","score":0.531000018119812}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7563538551330566},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7474863529205322},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.6206634044647217},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5722631812095642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5570465326309204},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5477126240730286},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4760603606700897},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4118485152721405},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.30145785212516785},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09334072470664978},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2963248502","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.10580.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}],"best_oa_location":{"id":"mag:2963248502","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.10580.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},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W187288179","https://openalex.org/W779494576","https://openalex.org/W1686946872","https://openalex.org/W1786044565","https://openalex.org/W1968768508","https://openalex.org/W1988526405","https://openalex.org/W2064675550","https://openalex.org/W2098774185","https://openalex.org/W2099111195","https://openalex.org/W2115807451","https://openalex.org/W2141124923","https://openalex.org/W2143435603","https://openalex.org/W2148989240","https://openalex.org/W2170503197","https://openalex.org/W2173248099","https://openalex.org/W2398870399","https://openalex.org/W2417786368","https://openalex.org/W2556477470","https://openalex.org/W2557579533","https://openalex.org/W2614839826","https://openalex.org/W2683470288","https://openalex.org/W2735995851","https://openalex.org/W2753738274","https://openalex.org/W2778065128","https://openalex.org/W2788741142","https://openalex.org/W2883433335","https://openalex.org/W2886000153","https://openalex.org/W2899205164","https://openalex.org/W2913854057","https://openalex.org/W2950040888","https://openalex.org/W2952581030","https://openalex.org/W6903351479"],"related_works":["https://openalex.org/W2980537796","https://openalex.org/W2913854057","https://openalex.org/W2912636986","https://openalex.org/W3034528880","https://openalex.org/W4400732445","https://openalex.org/W1970302770","https://openalex.org/W2990604886","https://openalex.org/W2343320077","https://openalex.org/W2556477470","https://openalex.org/W2911809292"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,57,67,100,111],"hierarchical":[3],"reinforcement":[4],"learning":[5,99],"(HRL)":[6],"or":[7,34,77],"options":[8,103],"framework":[9],"for":[10,27],"identifying":[11],"decision":[12,29,54,154,179,189],"states.":[13],"Informally":[14],"speaking,":[15],"these":[16,187],"are":[17],"states":[18,30,55,133,155,180,190],"considered":[19],"important":[20],"by":[21],"the":[22,128,132,137,147,149,157,168],"agent's":[23],"policy":[24],"e.g.":[25],",":[26],"navigation,":[28],"would":[31],"be":[32],"crossroads":[33],"doors":[35],"where":[36],"an":[37,106,142,182],"agent":[38,107,143],"needs":[39],"to":[40,108,144,192],"make":[41],"strategic":[42],"decisions.":[43],"While":[44],"previous":[45],"work":[46],"(most":[47],"notably":[48],"Goyal":[49],"et.":[50,92,96,121],"al.,":[51,93,97,122],"2019)":[52],"discovers":[53],"in":[56,66,136,181,195],"task/goal":[58],"specific":[59],"(or":[60,69],"'supervised')":[61],"manner,":[62,71,184],"we":[63],"do":[64],"so":[65],"goal-independent":[68],"'unsupervised')":[70],"i.e.":[72],"entirely":[73],"without":[74],"any":[75],"goal":[76],"extrinsic":[78],"rewards.":[79],"Our":[80,170],"approach":[81],"combines":[82],"two":[83],"hitherto":[84],"disparate":[85],"ideas":[86],"-":[87],"1)":[88,174],"\\emph{intrinsic":[89],"control}":[90],"(Gregor":[91],"2016,":[94],"Eysenbach":[95],"2018):":[98],"set":[101,113],"of":[102,114,153],"that":[104,173],"allow":[105],"reliably":[109,145],"reach":[110],"diverse":[112],"states,":[115],"and":[116,131,185,201],"2)":[117,186],"\\emph{information":[118],"bottleneck}":[119],"(Tishby":[120],"2000):":[123],"penalizing":[124],"mutual":[125,161],"information":[126,162],"between":[127],"option":[129],"$\\Omega$":[130],"$s_t$":[134],"visited":[135],"trajectory.":[138],"The":[139],"former":[140],"encourages":[141],"explore":[146],"environment;":[148],"latter":[150],"allows":[151],"identification":[152],"as":[156],"ones":[158],"with":[159],"high":[160],"$I(\\Omega;":[163],"a_t":[164],"|":[165],"s_t)$":[166],"despite":[167],"bottleneck.":[169],"results":[171],"demonstrate":[172],"our":[175],"model":[176],"learns":[177],"interpretable":[178],"unsupervised":[183],"learned":[188],"transfer":[191],"goal-driven":[193],"tasks":[194],"new":[196],"environments,":[197],"effectively":[198],"guide":[199],"exploration,":[200],"improve":[202],"performance.":[203]},"counts_by_year":[{"year":2020,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-07-30T00:00:00"}