{"id":"https://openalex.org/W4405786640","doi":"https://doi.org/10.1109/iros58592.2024.10801464","title":"Gradient-based Regularization for Action Smoothness in Robotic Control with Reinforcement Learning","display_name":"Gradient-based Regularization for Action Smoothness in Robotic Control with Reinforcement Learning","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405786640","doi":"https://doi.org/10.1109/iros58592.2024.10801464"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","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/A5090503795","display_name":"Ickjai Lee","orcid":"https://orcid.org/0000-0002-6886-6201"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"I Lee","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Department of Computer Science,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Department of Computer Science,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037550862","display_name":"Hoang-Giang Cao","orcid":"https://orcid.org/0009-0003-4692-5615"},"institutions":[{"id":"https://openalex.org/I12213908","display_name":"Ming Chi University of Technology","ror":"https://ror.org/04xgh4d03","country_code":"TW","type":"education","lineage":["https://openalex.org/I12213908"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hoang-Giang Cao","raw_affiliation_strings":["Ming Chi University of Technology,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ming Chi University of Technology,Taiwan","institution_ids":["https://openalex.org/I12213908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081832417","display_name":"Cong-Tinh Dao","orcid":"https://orcid.org/0000-0002-0777-6915"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cong-Tinh Dao","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Department of Computer Science,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Department of Computer Science,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100773467","display_name":"Yu\u2010Cheng Chen","orcid":"https://orcid.org/0000-0002-0008-5601"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Cheng Chen","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Department of Computer Science,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Department of Computer Science,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016730899","display_name":"I\u2010Chen Wu","orcid":"https://orcid.org/0000-0003-2535-0587"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"I-Chen Wu","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Department of Computer Science,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Department of Computer Science,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8739,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75964661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"603","last_page":"610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9297999739646912,"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":0.9297999739646912,"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":0.9193999767303467,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.835964560508728},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.661676287651062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6328300833702087},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.5717502236366272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5286227464675903},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.46397051215171814},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.42124977707862854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19321739673614502},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11562967300415039},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07218217849731445},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.058229923248291016}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.835964560508728},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.661676287651062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6328300833702087},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.5717502236366272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5286227464675903},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.46397051215171814},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.42124977707862854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19321739673614502},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11562967300415039},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07218217849731445},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.058229923248291016},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2733312032","https://openalex.org/W2808470116","https://openalex.org/W2973229164","https://openalex.org/W2982316857","https://openalex.org/W3135682060","https://openalex.org/W3207657697","https://openalex.org/W4312734823","https://openalex.org/W4389689603","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6767995479","https://openalex.org/W6794181181","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W2393022482","https://openalex.org/W2377346130","https://openalex.org/W2361092061","https://openalex.org/W2319775965","https://openalex.org/W2357314690","https://openalex.org/W4306904969","https://openalex.org/W2191886813","https://openalex.org/W1986317414","https://openalex.org/W2795976185","https://openalex.org/W2138720691"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"(DRL)":[3],"has":[4],"achieved":[5],"remarkable":[6],"success,":[7],"ranging":[8],"from":[9],"complex":[10],"computer":[11],"games":[12],"to":[13,83,116,120,122,192],"real-world":[14,32],"applications,":[15],"showing":[16],"the":[17,37,56,85,104,107,118,139,150],"potential":[18],"for":[19,72],"intelligent":[20],"agents":[21],"capable":[22],"of":[23,59,109,141,189],"learning":[24,158],"in":[25,31,40,106,168],"dynamic":[26],"environments.":[27,148,175],"However,":[28],"its":[29,162],"application":[30],"scenarios":[33,146],"presents":[34],"challenges,":[35],"including":[36],"jerky":[38,42,66],"problem,":[39],"which":[41],"trajectories":[43],"not":[44],"only":[45],"compromise":[46],"system":[47],"safety":[48],"but":[49],"also":[50],"increase":[51],"power":[52],"consumption":[53],"and":[54,61,111,138,147,160,172,194],"shorten":[55],"service":[57],"life":[58],"robotic":[60],"autonomous":[62],"systems.":[63],"To":[64],"address":[65],"actions,":[67],"a":[68,92,186],"method":[69,128,143],"called":[70],"conditioning":[71],"action":[73,86,110,124,132],"policy":[74,136],"smoothness":[75,190],"(CAPS)":[76],"was":[77],"proposed":[78],"by":[79,102],"adding":[80],"regularization":[81],"terms":[82],"reduce":[84],"changes.":[87],"This":[88],"paper":[89],"further":[90],"proposes":[91],"novel":[93],"method,":[94],"named":[95],"Gradient-based":[96],"CAPS":[97,101,193],"(Grad-CAPS),":[98],"that":[99,179],"modifies":[100],"reducing":[103],"difference":[105],"gradient":[108],"then":[112],"uses":[113],"displacement":[114],"normalization":[115],"enable":[117],"agent":[119],"adapt":[121],"invariant":[123],"scales.":[125],"Consequently,":[126],"our":[127,142],"effectively":[129,181],"reduces":[130],"zigzagging":[131],"sequences":[133],"while":[134,184],"enhancing":[135],"expressiveness":[137],"adaptability":[140],"across":[144],"diverse":[145],"In":[149],"experiments,":[151],"we":[152],"integrated":[153],"Grad-CAPS":[154,180],"with":[155],"different":[156],"reinforcement":[157],"algorithms":[159],"evaluated":[161],"performance":[163,183],"on":[164],"various":[165],"robotic-related":[166],"tasks":[167],"DeepMind":[169],"Control":[170],"Suite":[171],"OpenAI":[173],"Gym":[174],"The":[176],"results":[177],"demonstrate":[178],"improves":[182],"maintaining":[185],"comparable":[187],"level":[188],"compared":[191],"Vanilla":[195],"agents.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}