{"id":"https://openalex.org/W4226506398","doi":"https://doi.org/10.1007/978-3-031-21090-7_12","title":"Hierarchical Reinforcement Learning Under Mixed Observability","display_name":"Hierarchical Reinforcement Learning Under Mixed Observability","publication_year":2022,"publication_date":"2022-12-14","ids":{"openalex":"https://openalex.org/W4226506398","doi":"https://doi.org/10.1007/978-3-031-21090-7_12"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-21090-7_12","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-21090-7_12","pdf_url":null,"source":{"id":"https://openalex.org/S4210172544","display_name":"Springer proceedings in advanced robotics","issn_l":"2511-1256","issn":["2511-1256","2511-1264"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Springer Proceedings in Advanced Robotics","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037305946","display_name":"Van\u2010Dinh Nguyen","orcid":"https://orcid.org/0000-0002-9575-1063"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hai Nguyen","raw_affiliation_strings":["Khoury College of Computer Sciences, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Khoury College of Computer Sciences, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024368167","display_name":"Zhihan Yang","orcid":"https://orcid.org/0009-0004-1659-1404"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhihan Yang","raw_affiliation_strings":["Calerton College, Northfield, MN, USA"],"affiliations":[{"raw_affiliation_string":"Calerton College, Northfield, MN, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033275466","display_name":"Andrea Baisero","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea Baisero","raw_affiliation_strings":["Khoury College of Computer Sciences, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Khoury College of Computer Sciences, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101155264","display_name":"Xiao Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiao Ma","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072578581","display_name":"Robert W. Platt","orcid":"https://orcid.org/0000-0002-5981-8443"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Platt","raw_affiliation_strings":["Khoury College of Computer Sciences, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Khoury College of Computer Sciences, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033129735","display_name":"Christopher Amato","orcid":"https://orcid.org/0000-0002-6786-7384"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Amato","raw_affiliation_strings":["Khoury College of Computer Sciences, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Khoury College of Computer Sciences, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5037305946"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":0.6858,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69173187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"188","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9675999879837036,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.965399980545044,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.9646528363227844},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.811863899230957},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7519163489341736},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5709872245788574},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.45740440487861633},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.36966678500175476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30770957469940186},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.2606457471847534},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2343691885471344},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1949341595172882}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.9646528363227844},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.811863899230957},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7519163489341736},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5709872245788574},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.45740440487861633},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.36966678500175476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30770957469940186},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2606457471847534},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2343691885471344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1949341595172882},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-21090-7_12","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-21090-7_12","pdf_url":null,"source":{"id":"https://openalex.org/S4210172544","display_name":"Springer proceedings in advanced robotics","issn_l":"2511-1256","issn":["2511-1256","2511-1264"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Springer Proceedings in Advanced Robotics","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W40650588","https://openalex.org/W1981276685","https://openalex.org/W2011418219","https://openalex.org/W2064675550","https://openalex.org/W2121517924","https://openalex.org/W2157331557","https://openalex.org/W2158782408","https://openalex.org/W2295605012","https://openalex.org/W2583271265","https://openalex.org/W2747329762","https://openalex.org/W2802349643","https://openalex.org/W2912185451","https://openalex.org/W2963053311","https://openalex.org/W2964132611","https://openalex.org/W2967349569","https://openalex.org/W2968968734","https://openalex.org/W4252527162"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2967463586","https://openalex.org/W2765830098","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275","https://openalex.org/W4312300846","https://openalex.org/W2615757685","https://openalex.org/W11481024","https://openalex.org/W2999848267"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
