{"id":"https://openalex.org/W2735325244","doi":"https://doi.org/10.1007/s10994-017-5650-8","title":"Offline reinforcement learning with task hierarchies","display_name":"Offline reinforcement learning with task hierarchies","publication_year":2017,"publication_date":"2017-07-12","ids":{"openalex":"https://openalex.org/W2735325244","doi":"https://doi.org/10.1007/s10994-017-5650-8","mag":"2735325244"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-017-5650-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-017-5650-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-017-5650-8.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-017-5650-8.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005267157","display_name":"Devin Schwab","orcid":"https://orcid.org/0000-0003-0172-9744"},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Devin Schwab","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Case Western Reserve University, Cleveland, OH, 44106, USA"],"raw_orcid":"https://orcid.org/0000-0003-0172-9744","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Case Western Reserve University, Cleveland, OH, 44106, USA","institution_ids":["https://openalex.org/I58956616"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055101678","display_name":"Soumya Ray","orcid":"https://orcid.org/0000-0002-6673-6796"},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soumya Ray","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Case Western Reserve University, Cleveland, OH, 44106, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Case Western Reserve University, Cleveland, OH, 44106, USA","institution_ids":["https://openalex.org/I58956616"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005267157"],"corresponding_institution_ids":["https://openalex.org/I58956616"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":2.0786,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.90150496,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"106","issue":"9-10","first_page":"1569","last_page":"1598"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9904000163078308,"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":0.9850999712944031,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8997579216957092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7564891576766968},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7534429430961609},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.6792379021644592},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5999104976654053},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5958421230316162},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.553657054901123},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5425801873207092},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4507177770137787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4460660219192505},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.4375932514667511},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42648744583129883},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.41174110770225525},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3309459388256073},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3217013478279114},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2951531410217285},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13743850588798523}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8997579216957092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7564891576766968},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7534429430961609},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.6792379021644592},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5999104976654053},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5958421230316162},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.553657054901123},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5425801873207092},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4507177770137787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4460660219192505},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.4375932514667511},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42648744583129883},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.41174110770225525},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3309459388256073},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3217013478279114},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2951531410217285},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13743850588798523},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-017-5650-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-017-5650-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-017-5650-8.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-017-5650-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-017-5650-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-017-5650-8.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2735325244.pdf","grobid_xml":"https://content.openalex.org/works/W2735325244.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W189510620","https://openalex.org/W1514107797","https://openalex.org/W1556824961","https://openalex.org/W1557517019","https://openalex.org/W1585546214","https://openalex.org/W1586184796","https://openalex.org/W1592847719","https://openalex.org/W1870822514","https://openalex.org/W2089561656","https://openalex.org/W2101786389","https://openalex.org/W2109910161","https://openalex.org/W2119567691","https://openalex.org/W2121517924","https://openalex.org/W2130599357","https://openalex.org/W2134491302","https://openalex.org/W2143042284","https://openalex.org/W2145339207","https://openalex.org/W2153668164","https://openalex.org/W2158548602","https://openalex.org/W2167117774","https://openalex.org/W2257979135","https://openalex.org/W2335959470","https://openalex.org/W4249441547","https://openalex.org/W4285719527","https://openalex.org/W4298023569","https://openalex.org/W6680589169","https://openalex.org/W6683443546","https://openalex.org/W6684384772","https://openalex.org/W7001894244"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W4225571923"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}