{"id":"https://openalex.org/W2752954743","doi":"https://doi.org/10.1109/aim.2017.8014209","title":"Learning to walk with prior knowledge","display_name":"Learning to walk with prior knowledge","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2752954743","doi":"https://doi.org/10.1109/aim.2017.8014209","mag":"2752954743"},"language":"en","primary_location":{"id":"doi:10.1109/aim.2017.8014209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aim.2017.8014209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Advanced Intelligent Mechatronics (AIM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://mediatum.ub.tum.de/node?id=1430293","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065309879","display_name":"Martin Gottwald","orcid":"https://orcid.org/0000-0001-8486-126X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Gottwald","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Technische Universitat M\u00fcnchen Arcisstr. 21, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Technische Universitat M\u00fcnchen Arcisstr. 21, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026610704","display_name":"Dominik Meyer","orcid":"https://orcid.org/0000-0002-6948-9858"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dominik Meyer","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Technische Universitat M\u00fcnchen Arcisstr. 21, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Technische Universitat M\u00fcnchen Arcisstr. 21, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067323219","display_name":"Hao Shen","orcid":"https://orcid.org/0000-0001-7024-6573"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hao Shen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Technische Universitat M\u00fcnchen Arcisstr. 21, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Technische Universitat M\u00fcnchen Arcisstr. 21, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074346065","display_name":"Klaus Diepold","orcid":"https://orcid.org/0000-0003-0439-7511"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus Diepold","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Technische Universitat M\u00fcnchen Arcisstr. 21, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Technische Universitat M\u00fcnchen Arcisstr. 21, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1369","last_page":"1374"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9951000213623047,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.723213791847229},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.6976125240325928},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6962082982063293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5789878368377686},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5404037833213806},{"id":"https://openalex.org/keywords/weight","display_name":"Weight","score":0.5398496985435486},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.530833899974823},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.4410872757434845},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43388450145721436},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4333963990211487},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4215339422225952},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19522032141685486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.723213791847229},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.6976125240325928},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6962082982063293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5789878368377686},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5404037833213806},{"id":"https://openalex.org/C183877218","wikidata":"https://www.wikidata.org/wiki/Q7979858","display_name":"Weight","level":3,"score":0.5398496985435486},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.530833899974823},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.4410872757434845},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43388450145721436},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4333963990211487},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4215339422225952},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19522032141685486},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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},{"id":"https://openalex.org/C51568863","wikidata":"https://www.wikidata.org/wiki/Q664495","display_name":"Lie algebra","level":2,"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/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/aim.2017.8014209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aim.2017.8014209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Advanced Intelligent Mechatronics (AIM)","raw_type":"proceedings-article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1430293","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1430293","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1430293","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1430293","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6299999952316284,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1258105458","https://openalex.org/W2097381042","https://openalex.org/W2103285838","https://openalex.org/W2121863487","https://openalex.org/W2130791707","https://openalex.org/W2173248099","https://openalex.org/W2963864421","https://openalex.org/W4214717370","https://openalex.org/W6674600207","https://openalex.org/W6684921986","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3201126466","https://openalex.org/W4282827391","https://openalex.org/W4386828785","https://openalex.org/W3165580226","https://openalex.org/W3135401135","https://openalex.org/W2886688859","https://openalex.org/W4254199101","https://openalex.org/W3133164560","https://openalex.org/W3041001745","https://openalex.org/W4224526119"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"a":[3,69,107,151,181,190,204],"novel":[4],"approach":[5],"to":[6,79,140,143,163],"Transfer":[7,62],"Learning":[8,15],"for":[9,206,215],"the":[10,27,36,49,57,64,74,90,97,102,110,117,129,132,136,147,156,165,169,176,186,193,197],"use":[11],"in":[12,83,89,146,180,189],"Deep":[13,28],"Reinforcement":[14],"is":[16,20,66,114,161],"introduced.":[17],"The":[18,33,93],"agent":[19,187],"realized":[21],"as":[22,40,203],"an":[23,86],"actor-critic":[24],"framework,":[25],"namely":[26],"Deterministic":[29],"Policy":[30],"Gradient":[31],"algorithm.":[32],"Q-function":[34],"and":[35,54,125,135,188],"policy":[37,88,134],"are":[38,45,123],"represented":[39],"deep":[41],"feed-forward":[42],"networks,":[43],"that":[44,113,175],"trained":[46],"by":[47,55,168,185],"minimizing":[48],"mean":[50],"squared":[51],"Bellman":[52],"error":[53],"maximizing":[56],"expected":[58],"reward,":[59],"respectively.":[60],"For":[61],"Learning,":[63],"actor":[65],"modified":[67],"with":[68],"new":[70,137],"regularization":[71],"term,":[72],"called":[73],"knowledge":[75,82,94,177,198],"regularizer.":[76],"It":[77],"allows":[78],"include":[80],"prior":[81,157],"from":[84,155],"of":[85,109,131,192],"existing":[87,118,133],"learning":[91,194],"process.":[92],"regularizer":[95,178,199],"shifts":[96],"current":[98],"weight":[99,111,148],"vector":[100],"during":[101],"gradient":[103,166],"descent":[104],"step":[105],"towards":[106],"region":[108],"space,":[112],"centered":[115],"around":[116],"policy.":[119],"Because":[120],"neural":[121],"networks":[122],"universal":[124],"smooth":[126],"function":[127],"approximators,":[128],"weights":[130],"ones":[138],"have":[139],"lie":[141],"close":[142],"each":[144],"other":[145],"space.":[149],"Solving":[150],"task":[152],"therefore":[153],"benefits":[154],"knowledge,":[158],"when":[159],"it":[160,212],"used":[162,202],"manipulate":[164],"given":[167],"critic.":[170],"We":[171],"could":[172],"experimentally":[173],"verify,":[174],"results":[179],"higher":[182],"performance":[183],"achieved":[184],"reduction":[191],"time.":[195],"Furthermore,":[196],"can":[200],"be":[201],"replacement":[205],"labeled":[207],"training":[208],"data,":[209],"which":[210],"renders":[211],"especially":[213],"useful":[214],"physical":[216],"applications.":[217]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}