{"id":"https://openalex.org/W2978853121","doi":"https://doi.org/10.1109/devlrn.2019.8850699","title":"Reward-Punishment Actor-Critic Algorithm Applying to Robotic Non-grasping Manipulation","display_name":"Reward-Punishment Actor-Critic Algorithm Applying to Robotic Non-grasping Manipulation","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2978853121","doi":"https://doi.org/10.1109/devlrn.2019.8850699","mag":"2978853121"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2019.8850699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2019.8850699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://mediatum.ub.tum.de/node?id=1522788","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051304187","display_name":"Taisuke Kobayashi","orcid":"https://orcid.org/0000-0002-3760-249X"},"institutions":[{"id":"https://openalex.org/I4210127444","display_name":"Fraunhofer Institute for Cognitive Systems","ror":"https://ror.org/02fez3815","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127444","https://openalex.org/I4923324"]},{"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":true,"raw_author_name":"Taisuke Kobayashi","raw_affiliation_strings":["Institute for Cognitive Systems (ICS) Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Cognitive Systems (ICS) Technical University of Munich, Germany","institution_ids":["https://openalex.org/I4210127444","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060502779","display_name":"Takumi Aotani","orcid":"https://orcid.org/0000-0002-5774-767X"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takumi Aotani","raw_affiliation_strings":["Division of Information Science, Nara Institute of Science and Technology, Nara, Japan"],"affiliations":[{"raw_affiliation_string":"Division of Information Science, Nara Institute of Science and Technology, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076458394","display_name":"J. Rogelio Guadarrama-Olvera","orcid":"https://orcid.org/0000-0002-8967-9472"},"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"]},{"id":"https://openalex.org/I4210127444","display_name":"Fraunhofer Institute for Cognitive Systems","ror":"https://ror.org/02fez3815","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127444","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julio Rogelio Guadarrama-Olvera","raw_affiliation_strings":["Institute for Cognitive Systems (ICS) Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Cognitive Systems (ICS) Technical University of Munich, Germany","institution_ids":["https://openalex.org/I4210127444","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028782385","display_name":"Emmanuel Dean\u2010Leon","orcid":"https://orcid.org/0000-0002-1155-7088"},"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"]},{"id":"https://openalex.org/I4210127444","display_name":"Fraunhofer Institute for Cognitive Systems","ror":"https://ror.org/02fez3815","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127444","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Emmanuel Dean-Leon","raw_affiliation_strings":["Institute for Cognitive Systems (ICS) Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Cognitive Systems (ICS) Technical University of Munich, Germany","institution_ids":["https://openalex.org/I4210127444","https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048975019","display_name":"Gordon Cheng","orcid":"https://orcid.org/0000-0003-0770-8717"},"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"]},{"id":"https://openalex.org/I4210127444","display_name":"Fraunhofer Institute for Cognitive Systems","ror":"https://ror.org/02fez3815","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127444","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gordon Cheng","raw_affiliation_strings":["Institute for Cognitive Systems (ICS) Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Cognitive Systems (ICS) Technical University of Munich, Germany","institution_ids":["https://openalex.org/I4210127444","https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051304187"],"corresponding_institution_ids":["https://openalex.org/I4210127444","https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66161923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"17","issue":null,"first_page":"37","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9968000054359436,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9732000231742859,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/punishment","display_name":"Punishment (psychology)","score":0.7103736996650696},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6353081464767456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44828641414642334},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4158836007118225},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35871365666389465},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3419075608253479},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32046711444854736},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.25982362031936646},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.17623072862625122},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.13753777742385864}],"concepts":[{"id":"https://openalex.org/C2779295839","wikidata":"https://www.wikidata.org/wiki/Q3544090","display_name":"Punishment (psychology)","level":2,"score":0.7103736996650696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6353081464767456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44828641414642334},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4158836007118225},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35871365666389465},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3419075608253479},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32046711444854736},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25982362031936646},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.17623072862625122},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.13753777742385864}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/devlrn.2019.8850699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2019.8850699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","raw_type":"proceedings-article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1522788","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1522788","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/1522788","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1522788","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":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1191599655","https://openalex.org/W1828803485","https://openalex.org/W1845972764","https://openalex.org/W1972850108","https://openalex.org/W2015051472","https://openalex.org/W2022365837","https://openalex.org/W2084615382","https://openalex.org/W2101895600","https://openalex.org/W2118706537","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2141385700","https://openalex.org/W2156737235","https://openalex.org/W2172968643","https://openalex.org/W2257979135","https://openalex.org/W2269274350","https://openalex.org/W2613860617","https://openalex.org/W2726187156","https://openalex.org/W2795921402","https://openalex.org/W2900582619","https://openalex.org/W2952021385","https://openalex.org/W2962731213","https://openalex.org/W2962803570","https://openalex.org/W4293545785","https://openalex.org/W4295231058","https://openalex.org/W6639175102","https://openalex.org/W6683195989","https://openalex.org/W6737893269"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2053286651","https://openalex.org/W2181743346","https://openalex.org/W4285501642","https://openalex.org/W2187401768","https://openalex.org/W2181413294","https://openalex.org/W1982160337","https://openalex.org/W1808427767","https://openalex.org/W3191787099"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,10,143],"new":[4],"actor-critic":[5],"(AC)":[6],"algorithm":[7],"based":[8],"on":[9,181],"biological":[11],"reward-punishment":[12,64],"framework":[13],"for":[14,42],"reinforcement":[15],"learning":[16],"(RL),":[17],"named":[18],"\u201cRP-AC\u201d.":[19],"RL":[20,96],"can":[21,26],"yields":[22],"capabilities":[23],"where":[24],"robots":[25,66,103],"take":[27],"over":[28],"complicated":[29],"and":[30,51,59,79,90,130,151],"dangerous":[31,49],"tasks":[32],"instead":[33],"of":[34,76,87,138,194],"human.":[35],"Such":[36],"capability,":[37],"however,":[38],"may":[39],"require":[40],"accounting":[41],"safety":[43],"when":[44],"achieving":[45],"the":[46,55,63,74,85,106,125,154,168,174,183,188,191],"tasks,":[47],"because":[48],"states":[50],"actions":[52],"could":[53],"cause":[54],"robot":[56],"to":[57,101,127,172,177],"breakdown":[58],"induce":[60],"injuries.":[61],"In":[62,98,163],"framework,":[65],"gain":[67],"both":[68],"positive":[69],"reward":[70,81,129,150],"(called":[71,82],"reward)":[72],"as":[73,84,157],"degree":[75],"task":[77,165,175,189],"achievement":[78],"negative":[80],"punishment)":[83],"risk":[86],"current":[88],"state":[89],"action,":[91],"which":[92,109],"are":[93],"composed":[94],"in":[95,111,160],"algorithms.":[97],"this":[99,118],"paper,":[100],"control":[102],"more":[104,132],"directly,":[105],"AC":[107,170],"algorithm,":[108],"operate":[110],"continuous":[112],"action":[113],"space,":[114],"is":[115],"employed.":[116],"To":[117],"end,":[119],"we":[120,146],"propose":[121],"policy":[122,155],"gradients":[123],"with":[124,190],"way":[126],"compose":[128],"punishment,":[131],"accurately,":[133],"their":[134],"value":[135],"functions.":[136],"Instead":[137],"merely":[139],"composing":[140],"them":[141],"at":[142],"fixed":[144],"ratio,":[145],"theoretically":[147],"introduce":[148],"immediate":[149],"punishment":[152],"into":[153],"gradients,":[156],"animals":[158],"do":[159],"decision":[161],"making.":[162],"pushing":[164],"experiments,":[166],"whereas":[167],"vanilla":[169],"fails":[171],"acquire":[173],"due":[176],"too":[178],"much":[179],"emphasis":[180],"safety,":[182],"proposed":[184],"RP-AC":[185],"successfully":[186],"acquires":[187],"same":[192],"level":[193],"safety.":[195]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}