{"id":"https://openalex.org/W3112544284","doi":"https://doi.org/10.1109/icra48506.2021.9561138","title":"Regularizing Action Policies for Smooth Control with Reinforcement Learning","display_name":"Regularizing Action Policies for Smooth Control with Reinforcement Learning","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3112544284","doi":"https://doi.org/10.1109/icra48506.2021.9561138","mag":"3112544284"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2012.06644","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038185726","display_name":"Siddharth Mysore","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Siddharth Mysore","raw_affiliation_strings":["Boston University,Department of Computer Science,Boston,MA,02215"],"affiliations":[{"raw_affiliation_string":"Boston University,Department of Computer Science,Boston,MA,02215","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058159822","display_name":"Bassel Mabsout","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bassel Mabsout","raw_affiliation_strings":["Boston University,Department of Computer Science,Boston,MA,02215"],"affiliations":[{"raw_affiliation_string":"Boston University,Department of Computer Science,Boston,MA,02215","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035353750","display_name":"Renato Mancuso","orcid":"https://orcid.org/0000-0003-3558-5216"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Renato Mancuso","raw_affiliation_strings":["Boston University,Department of Computer Science,Boston,MA,02215"],"affiliations":[{"raw_affiliation_string":"Boston University,Department of Computer Science,Boston,MA,02215","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075906727","display_name":"Kate Saenko","orcid":"https://orcid.org/0000-0002-7564-7218"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kate Saenko","raw_affiliation_strings":["Boston University,Department of Computer Science,Boston,MA,02215","Boston Univ"],"affiliations":[{"raw_affiliation_string":"Boston University,Department of Computer Science,Boston,MA,02215","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Boston Univ","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038185726"],"corresponding_institution_ids":["https://openalex.org/I111088046"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60937335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1810","last_page":"1816"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9918000102043152,"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":0.9848999977111816,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8245989084243774},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6429716348648071},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.6261065006256104},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6137363314628601},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5347142815589905},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5210239887237549},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4962504506111145},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4822450578212738},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4437287151813507},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.36268967390060425},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18952986598014832},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15192356705665588}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8245989084243774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6429716348648071},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.6261065006256104},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6137363314628601},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5347142815589905},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5210239887237549},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4962504506111145},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4822450578212738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4437287151813507},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.36268967390060425},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18952986598014832},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15192356705665588},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icra48506.2021.9561138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2012.06644","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.06644","pdf_url":"https://arxiv.org/pdf/2012.06644","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:3112544284","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2012.06644.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":"pmh:oai:null:2144/43029","is_oa":false,"landing_page_url":"https://arxiv.org/abs/2012.06644","pdf_url":null,"source":{"id":"https://openalex.org/S4306402384","display_name":"OpenBU (Boston University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I111088046","host_organization_name":"Boston University","host_organization_lineage":["https://openalex.org/I111088046"],"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":"Article"},{"id":"doi:10.48550/arxiv.2012.06644","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2012.06644","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:2012.06644","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.06644","pdf_url":"https://arxiv.org/pdf/2012.06644","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/7","display_name":"Affordable and clean energy","score":0.5899999737739563}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3112544284.pdf"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1164749991","https://openalex.org/W1771410628","https://openalex.org/W2066260126","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2296691800","https://openalex.org/W2733312032","https://openalex.org/W2736601468","https://openalex.org/W2765691705","https://openalex.org/W2775954438","https://openalex.org/W2785678896","https://openalex.org/W2797527950","https://openalex.org/W2804900738","https://openalex.org/W2809668646","https://openalex.org/W2890803796","https://openalex.org/W2913859679","https://openalex.org/W2949608212","https://openalex.org/W2962890638","https://openalex.org/W2963641140","https://openalex.org/W2963864421","https://openalex.org/W2963923407","https://openalex.org/W2964294232","https://openalex.org/W2972646073","https://openalex.org/W2980070341","https://openalex.org/W2981021427","https://openalex.org/W2990747716","https://openalex.org/W2995617888","https://openalex.org/W2995894173","https://openalex.org/W3003669699","https://openalex.org/W3013688454","https://openalex.org/W3035493476","https://openalex.org/W3039737909","https://openalex.org/W3106462682","https://openalex.org/W6638018090","https://openalex.org/W6683204974","https://openalex.org/W6684921986","https://openalex.org/W6704571135","https://openalex.org/W6736987314","https://openalex.org/W6741002519","https://openalex.org/W6746914971","https://openalex.org/W6747473740","https://openalex.org/W6748582592","https://openalex.org/W6748839928","https://openalex.org/W6750181461","https://openalex.org/W6750629867","https://openalex.org/W6751889414","https://openalex.org/W6752431149","https://openalex.org/W6754615820","https://openalex.org/W6759231395","https://openalex.org/W6767995479","https://openalex.org/W6769739676","https://openalex.org/W6771730547","https://openalex.org/W6772196467","https://openalex.org/W6774807315","https://openalex.org/W6775341171","https://openalex.org/W6780559895","https://openalex.org/W6806532002"],"related_works":["https://openalex.org/W3207657697","https://openalex.org/W2966735560","https://openalex.org/W3210520478","https://openalex.org/W204050207","https://openalex.org/W3199735515","https://openalex.org/W2342231971","https://openalex.org/W3166834117","https://openalex.org/W2149398074","https://openalex.org/W3173811039","https://openalex.org/W2729602312","https://openalex.org/W2905364877","https://openalex.org/W2557003457","https://openalex.org/W3123748881","https://openalex.org/W3037396281","https://openalex.org/W3123933943","https://openalex.org/W2887709062","https://openalex.org/W3035493476","https://openalex.org/W30592968","https://openalex.org/W3049707075","https://openalex.org/W2948316777"],"abstract_inverted_index":{"A":[0],"critical":[1],"problem":[2],"with":[3,10],"the":[4,16,22,26,35,75,78,88,94],"practical":[5],"utility":[6],"of":[7,19,37,77,82,90],"controllers":[8],"trained":[9],"deep":[11],"Reinforcement":[12],"Learning":[13],"(RL)":[14],"is":[15],"notable":[17],"lack":[18],"smoothness":[20,76,105],"in":[21,34,44,74,87,93,103,111,116],"actions":[23],"learned":[24,79],"by":[25],"RL":[27],"policies.":[28],"This":[29],"trend":[30],"often":[31],"presents":[32],"itself":[33],"form":[36],"control":[38,95],"signal":[39],"oscillation":[40],"and":[41,50],"can":[42],"result":[43],"poor":[45],"control,":[46],"high":[47],"power":[48,117],"consumption,":[49],"undue":[51],"system":[52],"wear.":[53],"We":[54],"introduce":[55],"Conditioning":[56],"for":[57],"Action":[58],"Policy":[59],"Smoothness":[60],"(CAPS),":[61],"an":[62,112],"effective":[63],"yet":[64],"intuitive":[65],"regularization":[66],"on":[67,98,106],"action":[68],"policies,":[69],"which":[70],"offers":[71],"consistent":[72],"improvement":[73],"state-to-action":[80],"mappings":[81],"neural":[83],"network":[84],"controllers,":[85],"reflected":[86],"elimination":[89],"high-frequency":[91],"components":[92],"signal.":[96],"Tested":[97],"a":[99,107],"real":[100],"system,":[101],"improvements":[102],"controller":[104],"quadrotor":[108],"drone":[109],"resulted":[110],"almost":[113],"80%":[114],"reduction":[115],"consumption":[118],"while":[119],"consistently":[120],"training":[121],"flight-worthy":[122],"controllers.":[123],"Project":[124],"website:":[125],"http://ai.bu.edu/caps":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2022-07-25T00:00:00"}