{"id":"https://openalex.org/W4211089519","doi":"https://doi.org/10.1007/978-3-642-27645-3_18","title":"Reinforcement Learning in Robotics: A Survey","display_name":"Reinforcement Learning in Robotics: A Survey","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W4211089519","doi":"https://doi.org/10.1007/978-3-642-27645-3_18"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-27645-3_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-27645-3_18","pdf_url":null,"source":{"id":"https://openalex.org/S4210169857","display_name":"Adaptation, learning, and optimization","issn_l":"1867-4534","issn":["1867-4534","1867-4542"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptation, Learning, and Optimization","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/A5035229829","display_name":"Jens Kober","orcid":"https://orcid.org/0000-0001-7257-5434"},"institutions":[{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jens Kober","raw_affiliation_strings":["Intelligent Autonomous Systems Institute, Technische Universitaet Darmstadt, Darmstadt, Germany","Robot Learning Lab, Max-Planck Institute for Intelligent Systems, T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems Institute, Technische Universitaet Darmstadt, Darmstadt, Germany","institution_ids":[]},{"raw_affiliation_string":"Robot Learning Lab, Max-Planck Institute for Intelligent Systems, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210135521"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Intelligent Autonomous Systems Institute, Technische Universitaet Darmstadt, Darmstadt, Germany","Robot Learning Lab, Max-Planck Institute for Intelligent Systems, T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems Institute, Technische Universitaet Darmstadt, Darmstadt, Germany","institution_ids":[]},{"raw_affiliation_string":"Robot Learning Lab, Max-Planck Institute for Intelligent Systems, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210135521"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.2491,"has_fulltext":false,"cited_by_count":148,"citation_normalized_percentile":{"value":0.98043394,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"579","last_page":"610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9919999837875366,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9581999778747559,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9179182648658752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7071517705917358},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6543231010437012},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5787065029144287},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5693775415420532},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5589748024940491},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5542751550674438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5094464421272278},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4755691587924957},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43684303760528564},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3451630473136902},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3221905827522278},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19520783424377441},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.15579092502593994},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15555274486541748}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9179182648658752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7071517705917358},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6543231010437012},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5787065029144287},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5693775415420532},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5589748024940491},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5542751550674438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5094464421272278},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4755691587924957},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43684303760528564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3451630473136902},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3221905827522278},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19520783424377441},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.15579092502593994},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15555274486541748},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-642-27645-3_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-27645-3_18","pdf_url":null,"source":{"id":"https://openalex.org/S4210169857","display_name":"Adaptation, learning, and optimization","issn_l":"1867-4534","issn":["1867-4534","1867-4542"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptation, Learning, and Optimization","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":93,"referenced_works":["https://openalex.org/W49905056","https://openalex.org/W174941419","https://openalex.org/W356219054","https://openalex.org/W357338074","https://openalex.org/W606806978","https://openalex.org/W1435458549","https://openalex.org/W1491843047","https://openalex.org/W1499669280","https://openalex.org/W1500910471","https://openalex.org/W1507591516","https://openalex.org/W1509504119","https://openalex.org/W1511864092","https://openalex.org/W1516801383","https://openalex.org/W1517733364","https://openalex.org/W1545763673","https://openalex.org/W1580887022","https://openalex.org/W1599132676","https://openalex.org/W1626155273","https://openalex.org/W1755933627","https://openalex.org/W1949974402","https://openalex.org/W1964271816","https://openalex.org/W1967499360","https://openalex.org/W1975318316","https://openalex.org/W1979071892","https://openalex.org/W1985161922","https://openalex.org/W1986014385","https://openalex.org/W1988071341","https://openalex.org/W1994923984","https://openalex.org/W2021004298","https://openalex.org/W2026659355","https://openalex.org/W2033180067","https://openalex.org/W2035808435","https://openalex.org/W2041812416","https://openalex.org/W2042322703","https://openalex.org/W2042882799","https://openalex.org/W2051620263","https://openalex.org/W2070678636","https://openalex.org/W2073995413","https://openalex.org/W2080039641","https://openalex.org/W2096001037","https://openalex.org/W2100538121","https://openalex.org/W2107726111","https://openalex.org/W2108302062","https://openalex.org/W2108579172","https://openalex.org/W2109008048","https://openalex.org/W2109158177","https://openalex.org/W2118637732","https://openalex.org/W2120070743","https://openalex.org/W2123327324","https://openalex.org/W2125612430","https://openalex.org/W2127412976","https://openalex.org/W2127572219","https://openalex.org/W2129515556","https://openalex.org/W2132400125","https://openalex.org/W2132602063","https://openalex.org/W2133932631","https://openalex.org/W2139053308","https://openalex.org/W2142828048","https://openalex.org/W2146151428","https://openalex.org/W2150818585","https://openalex.org/W2151975555","https://openalex.org/W2152166054","https://openalex.org/W2152951714","https://openalex.org/W2157720571","https://openalex.org/W2158485545","https://openalex.org/W2159298583","https://openalex.org/W2161872510","https://openalex.org/W2162621328","https://openalex.org/W2162717641","https://openalex.org/W2163533082","https://openalex.org/W2164032318","https://openalex.org/W2167647761","https://openalex.org/W2168921921","https://openalex.org/W2168945912","https://openalex.org/W2169209873","https://openalex.org/W2170164558","https://openalex.org/W2172141376","https://openalex.org/W2172158418","https://openalex.org/W2172968643","https://openalex.org/W2184652140","https://openalex.org/W2198041288","https://openalex.org/W2294729144","https://openalex.org/W2312609093","https://openalex.org/W2331739408","https://openalex.org/W2489467106","https://openalex.org/W2591436094","https://openalex.org/W2595840341","https://openalex.org/W2725122918","https://openalex.org/W2993376333","https://openalex.org/W4235424703","https://openalex.org/W4243489454","https://openalex.org/W4249441547","https://openalex.org/W4396738453"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W4220829754","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W2171010636"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}