{"id":"https://openalex.org/W2973178003","doi":"https://doi.org/10.1007/978-3-030-67661-2_30","title":"Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning","display_name":"Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W2973178003","doi":"https://doi.org/10.1007/978-3-030-67661-2_30","mag":"2973178003"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-67661-2_30","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-67661-2_30","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1909.04134","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113845943","display_name":"Arjun Manoharan","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]},{"id":"https://openalex.org/I4210151956","display_name":"Robert Bosch (India)","ror":"https://ror.org/04my8ty22","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210151956","https://openalex.org/I889804353"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Arjun Manoharan","raw_affiliation_strings":["Indian Institute of Technology Madras, Chennai, India","Robert Bosch Centre for Data Science and AI, Chennai, India","Indian Institute of Technology Madras,Chennai,INDIA"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Robert Bosch Centre for Data Science and AI, Chennai, India","institution_ids":["https://openalex.org/I4210151956"]},{"raw_affiliation_string":"Indian Institute of Technology Madras,Chennai,INDIA","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085453702","display_name":"Rahul Ramesh","orcid":null},"institutions":[{"id":"https://openalex.org/I922845939","display_name":"Philadelphia University","ror":"https://ror.org/03zzmyz63","country_code":"US","type":"education","lineage":["https://openalex.org/I922845939"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Ramesh","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, USA","#N#               * University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, USA","institution_ids":["https://openalex.org/I922845939","https://openalex.org/I79576946"]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009374923","display_name":"Balaraman Ravindran","orcid":"https://orcid.org/0000-0002-5364-7639"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]},{"id":"https://openalex.org/I4210151956","display_name":"Robert Bosch (India)","ror":"https://ror.org/04my8ty22","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210151956","https://openalex.org/I889804353"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Balaraman Ravindran","raw_affiliation_strings":["Indian Institute of Technology Madras, Chennai, India","Robert Bosch Centre for Data Science and AI, Chennai, India","Indian Institute of Technology  Madras"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Robert Bosch Centre for Data Science and AI, Chennai, India","institution_ids":["https://openalex.org/I4210151956"]},{"raw_affiliation_string":"Indian Institute of Technology  Madras","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113845943"],"corresponding_institution_ids":["https://openalex.org/I24676775","https://openalex.org/I4210151956"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00303357,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"509","last_page":"524"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9898999929428101,"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/computer-science","display_name":"Computer science","score":0.7704672813415527},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.767533540725708},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.658755898475647},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5708365440368652},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5652638077735901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47919902205467224},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.4615722894668579},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44262734055519104},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4383108615875244},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10923033952713013},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07994866371154785}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7704672813415527},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.767533540725708},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.658755898475647},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5708365440368652},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5652638077735901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47919902205467224},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.4615722894668579},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44262734055519104},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4383108615875244},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10923033952713013},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07994866371154785},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating 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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/978-3-030-67661-2_30","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-67661-2_30","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:1909.04134","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.04134","pdf_url":"https://arxiv.org/pdf/1909.04134","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"},{"id":"mag:2973178003","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1909.04134.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1909.04134","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1909.04134","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1909.04134","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.04134","pdf_url":"https://arxiv.org/pdf/1909.04134","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1536990779","https://openalex.org/W1968768508","https://openalex.org/W2090170171","https://openalex.org/W2106008664","https://openalex.org/W2106261932","https://openalex.org/W2109910161","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2143435603","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2161795906","https://openalex.org/W2168640731","https://openalex.org/W2173248099","https://openalex.org/W2174786457","https://openalex.org/W2215010794","https://openalex.org/W2257979135","https://openalex.org/W2260756217","https://openalex.org/W2312609093","https://openalex.org/W2334782222","https://openalex.org/W2560647685","https://openalex.org/W2583761661","https://openalex.org/W2736601468","https://openalex.org/W2789008106","https://openalex.org/W2949267040","https://openalex.org/W2949608212","https://openalex.org/W2950040888","https://openalex.org/W2963438456","https://openalex.org/W2963946410","https://openalex.org/W2964043796","https://openalex.org/W2964227312","https://openalex.org/W2971273232","https://openalex.org/W6636592841","https://openalex.org/W6777094737","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W2097828232","https://openalex.org/W2965666670","https://openalex.org/W2963912551","https://openalex.org/W3092418144","https://openalex.org/W2169006000","https://openalex.org/W31377030","https://openalex.org/W1677904636","https://openalex.org/W2127288102","https://openalex.org/W2106216543","https://openalex.org/W3134613326","https://openalex.org/W3105525188","https://openalex.org/W2965762627","https://openalex.org/W2570364481","https://openalex.org/W2064567069","https://openalex.org/W2240922584","https://openalex.org/W971255375","https://openalex.org/W1036107598","https://openalex.org/W3088052656","https://openalex.org/W1549848204","https://openalex.org/W3080814299"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}