{"id":"https://openalex.org/W2146679853","doi":"https://doi.org/10.1109/iros.2007.4399219","title":"An extended policy gradient algorithm for robot task learning","display_name":"An extended policy gradient algorithm for robot task learning","publication_year":2007,"publication_date":"2007-10-01","ids":{"openalex":"https://openalex.org/W2146679853","doi":"https://doi.org/10.1109/iros.2007.4399219","mag":"2146679853"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2007.4399219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2007.4399219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01247244","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022568011","display_name":"Andrea Cherubini","orcid":"https://orcid.org/0000-0002-7272-6922"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"A. Cherubini","raw_affiliation_strings":["Dipartimento di Informatica e Sistemistica, University of Roma La Sapienza, Rome, Italy","Sapienza Univ. of Roma, Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica e Sistemistica, University of Roma La Sapienza, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Sapienza Univ. of Roma, Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078913873","display_name":"Elisa Giannone","orcid":null},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"E. Giannone","raw_affiliation_strings":["Dipartimento di Informatica e Sistemistica, University of Roma La Sapienza, Rome, Italy","Sapienza Univ. of Roma, Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica e Sistemistica, University of Roma La Sapienza, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Sapienza Univ. of Roma, Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026692089","display_name":"Luca Iocchi","orcid":"https://orcid.org/0000-0001-9057-8946"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"L. Iocchi","raw_affiliation_strings":["Dipartimento di Informatica e Sistemistica, University of Roma La Sapienza, Rome, Italy","Sapienza Univ. of Roma, Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica e Sistemistica, University of Roma La Sapienza, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Sapienza Univ. of Roma, Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105859012","display_name":"P. E. Palamara","orcid":null},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"P. E. Palamara","raw_affiliation_strings":["Dipartimento di Informatica e Sistemistica, University of Roma La Sapienza, Rome, Italy","Sapienza Univ. of Roma, Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica e Sistemistica, University of Roma La Sapienza, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Sapienza Univ. of Roma, Rome","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"4121","last_page":"4126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9954000115394592,"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"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9904999732971191,"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":0.8031028509140015},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7344040274620056},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7167722582817078},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.635572612285614},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5746747255325317},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.483423113822937},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4789350926876068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4760979413986206},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.46570900082588196},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4644940197467804},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.44626232981681824},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4316340386867523},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34345293045043945},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3010184168815613},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10632234811782837}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8031028509140015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7344040274620056},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7167722582817078},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.635572612285614},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5746747255325317},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.483423113822937},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4789350926876068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4760979413986206},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.46570900082588196},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4644940197467804},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.44626232981681824},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4316340386867523},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34345293045043945},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3010184168815613},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10632234811782837},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/iros.2007.4399219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2007.4399219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.499.1261","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.499.1261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dis.uniroma1.it/~labrob/people/cherubini/assets/files/extendedPG-IROS.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.7867","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.7867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dis.uniroma1.it/~iocchi/publications/iocchi-iros07.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-01247244v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01247244","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, IROS'07, Oct 2007, San Diego, United States. ⟨10.1109/IROS.2007.4399219⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:iris.uniroma1.it:11573/358629","is_oa":false,"landing_page_url":"http://hdl.handle.net/11573/358629","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01247244v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01247244","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, IROS'07, Oct 2007, San Diego, United States. ⟨10.1109/IROS.2007.4399219⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.75,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1576818901","https://openalex.org/W1674316932","https://openalex.org/W1744661136","https://openalex.org/W1899059484","https://openalex.org/W2104112233","https://openalex.org/W2121863487","https://openalex.org/W2139053308","https://openalex.org/W2155027007","https://openalex.org/W2160264739","https://openalex.org/W2890603939","https://openalex.org/W2914048451","https://openalex.org/W4214717370","https://openalex.org/W6636980921","https://openalex.org/W6637791136","https://openalex.org/W6639787226","https://openalex.org/W6675422434","https://openalex.org/W6683204974"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W3127551068","https://openalex.org/W4365788246"],"abstract_inverted_index":{"In":[0,55,97],"real-world":[1],"robotic":[2],"applications,":[3,83],"many":[4,30],"factors,":[5],"both":[6],"at":[7,16],"low-level":[8],"(e.g.,":[9,18],"vision":[10],"and":[11,15,44,110,131],"motion":[12],"control":[13,46],"parameters)":[14],"high-level":[17],"the":[19,22,25,37,40,115],"behaviors)":[20],"determine":[21],"quality":[23],"of":[24,36,42,75,95,107,123],"robot":[26,135],"performance.":[27],"Thus,":[28],"for":[29,69,86,104],"tasks,":[31],"robots":[32,88],"require":[33],"fine":[34],"tuning":[35],"parameters,":[38,112],"in":[39,51,81,127],"implementation":[41],"behaviors":[43],"basic":[45],"actions,":[47],"as":[48,50],"well":[49],"strategic":[52],"decisional":[53],"processes.":[54],"recent":[56],"years,":[57],"machine":[58],"learning":[59,76,106,119],"techniques":[60,77],"have":[61],"been":[62],"used":[63],"to":[64],"find":[65],"optimal":[66,111],"parameter":[67],"sets":[68],"different":[70],"behaviors.":[71],"However,":[72],"a":[73,102,128,133,137],"drawback":[74],"is":[78],"time":[79],"consumption:":[80],"practical":[82],"methods":[84],"designed":[85],"physical":[87],"must":[89],"be":[90],"effective":[91],"with":[92],"small":[93],"amounts":[94],"data.":[96],"this":[98],"paper,":[99],"we":[100],"present":[101],"method":[103],"concurrent":[105],"best":[108],"strategy":[109],"by":[113],"extending":[114],"policy":[116],"gradient":[117],"reinforcement":[118],"algorithm.":[120],"The":[121],"results":[122],"our":[124],"experimental":[125],"work":[126],"simulated":[129],"environment":[130],"on":[132],"real":[134],"show":[136],"very":[138],"high":[139],"convergence":[140],"rate.":[141]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}