{"id":"https://openalex.org/W2891162089","doi":"https://doi.org/10.1109/icra.2018.8461153","title":"Reinforcement Learning for 4-Finger-Gripper Manipulation","display_name":"Reinforcement Learning for 4-Finger-Gripper Manipulation","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2891162089","doi":"https://doi.org/10.1109/icra.2018.8461153","mag":"2891162089"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2018.8461153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8461153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","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/A5068715875","display_name":"Marco Ojer","orcid":"https://orcid.org/0000-0002-4494-6688"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Marco Ojer De Andres","raw_affiliation_strings":["Mahdi Ghazaei is with the Department of Advanced Robotics (ADVR), Italian Institute of Technology (IIT)"],"affiliations":[{"raw_affiliation_string":"Mahdi Ghazaei is with the Department of Advanced Robotics (ADVR), Italian Institute of Technology (IIT)","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018190451","display_name":"M. Mahdi Ghazaei Ardakani","orcid":"https://orcid.org/0000-0002-4713-1003"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"M. Mahdi Ghazaei Ardakani","raw_affiliation_strings":["Mahdi Ghazaei is with the Department of Advanced Robotics (ADVR), Italian Institute of Technology (IIT)"],"affiliations":[{"raw_affiliation_string":"Mahdi Ghazaei is with the Department of Advanced Robotics (ADVR), Italian Institute of Technology (IIT)","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013736282","display_name":"Anders Robertsson","orcid":"https://orcid.org/0000-0003-1063-4771"},"institutions":[{"id":"https://openalex.org/I187531555","display_name":"Lund University","ror":"https://ror.org/012a77v79","country_code":"SE","type":"education","lineage":["https://openalex.org/I187531555"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Anders Robertsson","raw_affiliation_strings":["Anders Robertsson is with the Department of Automatic Control, Lund University, Lund, Sweden"],"affiliations":[{"raw_affiliation_string":"Anders Robertsson is with the Department of Automatic Control, Lund University, Lund, Sweden","institution_ids":["https://openalex.org/I187531555"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068715875"],"corresponding_institution_ids":["https://openalex.org/I30771326"],"apc_list":null,"apc_paid":null,"fwci":0.6769,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77896251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4257","last_page":"4262"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9976000189781189,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8407772779464722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6573193073272705},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6512734293937683},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5966851711273193},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5937698483467102},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5901839733123779},{"id":"https://openalex.org/keywords/racket","display_name":"Racket","score":0.5144896507263184},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.43503338098526},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4232974052429199},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1675364077091217},{"id":"https://openalex.org/keywords/swing","display_name":"Swing","score":0.0763750672340393}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8407772779464722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6573193073272705},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6512734293937683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5966851711273193},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5937698483467102},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5901839733123779},{"id":"https://openalex.org/C2778707667","wikidata":"https://www.wikidata.org/wiki/Q1254148","display_name":"Racket","level":3,"score":0.5144896507263184},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.43503338098526},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4232974052429199},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1675364077091217},{"id":"https://openalex.org/C65655974","wikidata":"https://www.wikidata.org/wiki/Q14867674","display_name":"Swing","level":2,"score":0.0763750672340393},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2018.8461153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8461153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321806","display_name":"Lunds Universitet","ror":"https://ror.org/012a77v79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W271484250","https://openalex.org/W1977655452","https://openalex.org/W2016765487","https://openalex.org/W2019048916","https://openalex.org/W2042882799","https://openalex.org/W2071841410","https://openalex.org/W2100235553","https://openalex.org/W2123967136","https://openalex.org/W2153652631","https://openalex.org/W2560304127","https://openalex.org/W2577316117","https://openalex.org/W2604726708","https://openalex.org/W2620853513","https://openalex.org/W3005581722","https://openalex.org/W6640290305","https://openalex.org/W6654705334","https://openalex.org/W6661204239","https://openalex.org/W6674795239","https://openalex.org/W6678157427","https://openalex.org/W6732262396","https://openalex.org/W6736742618"],"related_works":["https://openalex.org/W2744434216","https://openalex.org/W2744749537","https://openalex.org/W598786559","https://openalex.org/W2489491829","https://openalex.org/W2744275524","https://openalex.org/W2589774136","https://openalex.org/W2580283794","https://openalex.org/W2370107557","https://openalex.org/W1599896731","https://openalex.org/W2106440236"],"abstract_inverted_index":{"In":[0],"the":[1,10,16,27,30,49,67,81,89,103,106,110,114],"framework":[2],"of":[3,12,69,83,91,105,113],"robotics,":[4],"Reinforcement":[5],"Learning":[6],"(RL)":[7],"deals":[8],"with":[9,56,125],"learning":[11],"a":[13,22,37,84,94,97,129],"task":[14,90,115],"by":[15,72],"robot":[17,28],"itself.":[18],"This":[19],"paper":[20,79],"presents":[21],"hierarchical-planning":[23],"approach":[24],"in":[25,36,123,128],"which":[26,87],"learns":[29],"optimal":[31],"behavior":[32],"for":[33,48],"different":[34],"levels":[35],"decoupled":[38],"way.":[39],"For":[40],"high-level":[41],"discrete":[42],"actions,":[43],"Q-learning":[44],"was":[45],"chosen,":[46],"whereas":[47],"low":[50],"level":[51],"we":[52],"utilize":[53],"Policy":[54],"Improvement":[55],"Path":[57],"Integrals":[58],"(PI":[59],"<sup":[60,118],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[61,119],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[62,120],")":[63],"algorithm":[64],"to":[65],"learn":[66],"parameters":[68],"policies,":[70],"represented":[71],"rhythmic":[73,126],"Dynamic":[74],"Movement":[75],"Primitives":[76],"(DMPs).":[77],"The":[78,100],"studies":[80],"case":[82],"4-finger-gripper":[85],"manipulator,":[86],"performs":[88],"continuously":[92],"spinning":[93],"ball":[95],"around":[96],"desired":[98],"axis.":[99],"results":[101],"demonstrate":[102],"efficacy":[104],"hierarchical":[107],"planning":[108],"and":[109],"increased":[111],"performance":[112],"when":[116],"PI":[117],"is":[121],"used":[122],"conjunction":[124],"DMPs":[127],"real":[130],"environment.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}