{"id":"https://openalex.org/W2046669420","doi":"https://doi.org/10.1109/humanoids.2014.7041389","title":"Robust policy updates for stochastic optimal control","display_name":"Robust policy updates for stochastic optimal control","publication_year":2014,"publication_date":"2014-11-01","ids":{"openalex":"https://openalex.org/W2046669420","doi":"https://doi.org/10.1109/humanoids.2014.7041389","mag":"2046669420"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids.2014.7041389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2014.7041389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE-RAS International Conference on Humanoid Robots","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Robust_policy_updates_for_stochastic_optimal_control/25171235","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037230603","display_name":"Elmar Rueckert","orcid":"https://orcid.org/0000-0003-1221-8253"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Elmar Rueckert","raw_affiliation_strings":["Intelligent Autonomous Systems Lab, Technische Universitat Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems Lab, Technische Universitat Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025310691","display_name":"Max Mindt","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Max Mindt","raw_affiliation_strings":["Intelligent Autonomous Systems Lab, Technische Universitat Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems Lab, Technische Universitat Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"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 Lab, Technische Universitat Darmstadt, Darmstadt, Germany","Robot Learning Group, Max-Planck Institute for Intelligent Systems, Tuebingen, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems Lab, Technische Universitat Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Robot Learning Group, Max-Planck Institute for Intelligent Systems, Tuebingen, Germany","institution_ids":["https://openalex.org/I4210135521"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110467801","display_name":"Gerhard Neumann","orcid":"https://orcid.org/0000-0002-5483-4225"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerhard Neumann","raw_affiliation_strings":["Computational Learning for Autonomous Systems, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Computational Learning for Autonomous Systems, Darmstadt, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5037230603"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":1.1542,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78135719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"388","last_page":"393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10879","display_name":"Robotic Locomotion and Control","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.9765999913215637,"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":0.6100742220878601},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5530668497085571},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5485027432441711},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5319217443466187},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.49202534556388855},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.46366313099861145},{"id":"https://openalex.org/keywords/trajectory-optimization","display_name":"Trajectory optimization","score":0.46243536472320557},{"id":"https://openalex.org/keywords/taylor-series","display_name":"Taylor series","score":0.4576590955257416},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.44516605138778687},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.43572473526000977},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2875061631202698},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26809608936309814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19148236513137817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6100742220878601},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5530668497085571},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5485027432441711},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5319217443466187},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.49202534556388855},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.46366313099861145},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.46243536472320557},{"id":"https://openalex.org/C158946198","wikidata":"https://www.wikidata.org/wiki/Q131187","display_name":"Taylor series","level":2,"score":0.4576590955257416},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.44516605138778687},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.43572473526000977},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2875061631202698},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26809608936309814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19148236513137817},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/humanoids.2014.7041389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2014.7041389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE-RAS International Conference on Humanoid Robots","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.lincoln.ac.uk:25754","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196275","display_name":"Lincoln Repository (University of Lincoln)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I51532219","host_organization_name":"University of Lincoln","host_organization_lineage":["https://openalex.org/I51532219"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop contribution"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.655.5914","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.655.5914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ausy.informatik.tu-darmstadt.de/uploads/Site/EditPublication/AICOHumanoidsFinal.pdf","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/25171235","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Robust_policy_updates_for_stochastic_optimal_control/25171235","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/25171235","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Robust_policy_updates_for_stochastic_optimal_control/25171235","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1514989902","https://openalex.org/W1581095231","https://openalex.org/W1939926247","https://openalex.org/W1941248864","https://openalex.org/W1981483064","https://openalex.org/W1988472059","https://openalex.org/W1988609580","https://openalex.org/W2036096913","https://openalex.org/W2087617385","https://openalex.org/W2107464055","https://openalex.org/W2107662876","https://openalex.org/W2109169869","https://openalex.org/W2111467524","https://openalex.org/W2117567237","https://openalex.org/W2123157758","https://openalex.org/W2138971019","https://openalex.org/W2142242920","https://openalex.org/W2156243072","https://openalex.org/W2164429173","https://openalex.org/W2167856595","https://openalex.org/W2168921921","https://openalex.org/W2180150039","https://openalex.org/W2543071036","https://openalex.org/W4240196545","https://openalex.org/W6640661648","https://openalex.org/W6676556483","https://openalex.org/W6677169258","https://openalex.org/W6681017831"],"related_works":["https://openalex.org/W4385832323","https://openalex.org/W2356996864","https://openalex.org/W4244391535","https://openalex.org/W2015393961","https://openalex.org/W2904060783","https://openalex.org/W2378339670","https://openalex.org/W2359353485","https://openalex.org/W2139910871","https://openalex.org/W2361427670","https://openalex.org/W2886240924"],"abstract_inverted_index":{"For":[0],"controlling":[1],"high-dimensional":[2],"robots,":[3],"most":[4],"stochastic":[5],"optimal":[6],"control":[7],"algorithms":[8,47],"use":[9],"approximations":[10,27],"of":[11,16,97,148],"the":[12,17,38,46,59,69,78,85,124,129],"system":[13],"dynamics":[14],"and":[15,23,140],"cost":[18,60],"function":[19,61],"(e.g.,":[20],"using":[21],"linearizations":[22],"Taylor":[24],"expansions).":[25],"These":[26],"are":[28],"typically":[29],"only":[30],"locally":[31],"correct,":[32],"which":[33],"might":[34],"cause":[35],"instabilities":[36],"in":[37,68],"greedy":[39],"policy":[40,65],"updates,":[41],"lead":[42],"to":[43,58,77],"oscillations":[44],"or":[45,150],"diverge.":[48],"To":[49],"overcome":[50],"these":[51],"drawbacks,":[52],"we":[53,133],"add":[54],"a":[55],"regularization":[56],"term":[57],"that":[62],"punishes":[63],"large":[64],"update":[66],"steps":[67],"trajectory":[70],"optimization":[71],"procedure.":[72],"We":[73,100],"applied":[74],"this":[75],"concept":[76],"Approximate":[79],"Inference":[80],"Control":[81],"method":[82],"(AICO),":[83],"where":[84],"resulting":[86],"algorithm":[87,104],"guarantees":[88],"convergence":[89],"for":[90,118],"uninformative":[91],"initial":[92],"solutions":[93],"without":[94],"complex":[95,136],"hand-tuning":[96],"learning":[98],"rates.":[99],"evaluated":[101],"our":[102],"new":[103],"on":[105],"two":[106],"simulated":[107],"robotic":[108],"platforms.":[109],"A":[110],"robot":[111,131],"arm":[112],"with":[113],"five":[114],"joints":[115],"was":[116],"used":[117],"reaching":[119,139],"multiple":[120],"targets":[121],"while":[122],"keeping":[123],"roll":[125],"angle":[126],"constant.":[127],"On":[128],"humanoid":[130],"Nao,":[132],"show":[134],"how":[135],"skills":[137],"like":[138],"balancing":[141],"can":[142],"be":[143],"inferred":[144],"from":[145],"desired":[146],"center":[147],"gravity":[149],"end":[151],"effector":[152],"coordinates.":[153]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}