{"id":"https://openalex.org/W3029338434","doi":"https://doi.org/10.1007/978-3-030-43089-4_43","title":"SWIRL: A SequentialWindowed Inverse Reinforcement Learning Algorithm for Robot Tasks With Delayed Rewards","display_name":"SWIRL: A SequentialWindowed Inverse Reinforcement Learning Algorithm for Robot Tasks With Delayed Rewards","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3029338434","doi":"https://doi.org/10.1007/978-3-030-43089-4_43","mag":"3029338434"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-43089-4_43","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-43089-4_43","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/A5018480426","display_name":"Sanjay Krishnan","orcid":"https://orcid.org/0000-0001-6968-4090"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I4210153740","display_name":"Berkeley Systems (United States)","ror":"https://ror.org/05sb0mt20","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153740"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sanjay Krishnan","raw_affiliation_strings":["The AUTOLAB at UC, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"The AUTOLAB at UC, Berkeley, USA","institution_ids":["https://openalex.org/I4210153740","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061193324","display_name":"Animesh Garg","orcid":"https://orcid.org/0000-0003-0482-4296"},"institutions":[{"id":"https://openalex.org/I4210153740","display_name":"Berkeley Systems (United States)","ror":"https://ror.org/05sb0mt20","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153740"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Animesh Garg","raw_affiliation_strings":["The AUTOLAB at UC, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"The AUTOLAB at UC, Berkeley, USA","institution_ids":["https://openalex.org/I4210153740","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075667645","display_name":"Richard Liaw","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153740","display_name":"Berkeley Systems (United States)","ror":"https://ror.org/05sb0mt20","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153740"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Liaw","raw_affiliation_strings":["The AUTOLAB at UC, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"The AUTOLAB at UC, Berkeley, USA","institution_ids":["https://openalex.org/I4210153740","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055891784","display_name":"Brijen Thananjeyan","orcid":"https://orcid.org/0000-0003-1841-5071"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I4210153740","display_name":"Berkeley Systems (United States)","ror":"https://ror.org/05sb0mt20","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153740"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brijen Thananjeyan","raw_affiliation_strings":["The AUTOLAB at UC, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"The AUTOLAB at UC, Berkeley, USA","institution_ids":["https://openalex.org/I4210153740","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021534233","display_name":"Lauren Miller","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I4210153740","display_name":"Berkeley Systems (United States)","ror":"https://ror.org/05sb0mt20","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153740"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lauren Miller","raw_affiliation_strings":["The AUTOLAB at UC, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"The AUTOLAB at UC, Berkeley, USA","institution_ids":["https://openalex.org/I4210153740","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018027629","display_name":"Florian T. Pokorny","orcid":"https://orcid.org/0000-0003-1114-6040"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Florian T. Pokorny","raw_affiliation_strings":["CAS/CVAP, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"CAS/CVAP, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050342525","display_name":"Ken Goldberg","orcid":"https://orcid.org/0000-0002-2661-4524"},"institutions":[{"id":"https://openalex.org/I4210153740","display_name":"Berkeley Systems (United States)","ror":"https://ror.org/05sb0mt20","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153740"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ken Goldberg","raw_affiliation_strings":["The AUTOLAB at UC, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"The AUTOLAB at UC, Berkeley, USA","institution_ids":["https://openalex.org/I4210153740","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5018480426"],"corresponding_institution_ids":["https://openalex.org/I4210153740","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":2.4731,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.87865619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"672","last_page":"687"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7344380617141724},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5924522280693054},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5806748270988464},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5553596019744873},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.513771653175354},{"id":"https://openalex.org/keywords/inverse-dynamics","display_name":"Inverse dynamics","score":0.5002477169036865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4843924641609192},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4392934739589691},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4342750310897827},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.42875608801841736},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3765488266944885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2648787498474121},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13610422611236572},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.07036042213439941}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7344380617141724},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5924522280693054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5806748270988464},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5553596019744873},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.513771653175354},{"id":"https://openalex.org/C187523126","wikidata":"https://www.wikidata.org/wiki/Q17098330","display_name":"Inverse dynamics","level":3,"score":0.5002477169036865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4843924641609192},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4392934739589691},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4342750310897827},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.42875608801841736},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3765488266944885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2648787498474121},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13610422611236572},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.07036042213439941},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-43089-4_43","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-43089-4_43","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W979233906","https://openalex.org/W1482341360","https://openalex.org/W1584687743","https://openalex.org/W1986014385","https://openalex.org/W1999303932","https://openalex.org/W1999874108","https://openalex.org/W2022760091","https://openalex.org/W2091797369","https://openalex.org/W2135043890","https://openalex.org/W2161395589","https://openalex.org/W2211996086","https://openalex.org/W2415633882","https://openalex.org/W2602024037","https://openalex.org/W6637681330"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W2218699221","https://openalex.org/W2136202932","https://openalex.org/W4312713068","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W1996614427","https://openalex.org/W2361647908"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
