{"id":"https://openalex.org/W2786878425","doi":"https://doi.org/10.1109/ssci.2017.8280919","title":"Gradient-based minimization for multi-expert Inverse Reinforcement Learning","display_name":"Gradient-based minimization for multi-expert Inverse Reinforcement Learning","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2786878425","doi":"https://doi.org/10.1109/ssci.2017.8280919","mag":"2786878425"},"language":"en","primary_location":{"id":"doi:10.1109/ssci.2017.8280919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2017.8280919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5001304610","display_name":"Davide Tateo","orcid":"https://orcid.org/0000-0002-7193-923X"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Tateo","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091526684","display_name":"Matteo Pirotta","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Matteo Pirotta","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017130830","display_name":"Marcello Restelli","orcid":"https://orcid.org/0000-0002-6322-1076"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marcello Restelli","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060263666","display_name":"Andrea Bonarini","orcid":"https://orcid.org/0000-0002-4880-4521"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Bonarini","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"51","issue":null,"first_page":"1","last_page":"8"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.995199978351593,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9896000027656555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7382864952087402},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.6567941308021545},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6563074588775635},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5999480485916138},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5352243781089783},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4500860273838043},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.4468895196914673},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4135569632053375},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15429523587226868}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7382864952087402},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.6567941308021545},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6563074588775635},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5999480485916138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5352243781089783},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4500860273838043},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4468895196914673},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4135569632053375},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15429523587226868},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ssci.2017.8280919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2017.8280919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1045585","is_oa":false,"landing_page_url":"http://hdl.handle.net/11311/1045585","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5199999809265137,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W973495809","https://openalex.org/W1506806321","https://openalex.org/W1559990548","https://openalex.org/W1567876833","https://openalex.org/W1591675293","https://openalex.org/W1652033540","https://openalex.org/W1681245057","https://openalex.org/W1968154520","https://openalex.org/W1986014385","https://openalex.org/W1999874108","https://openalex.org/W2012587148","https://openalex.org/W2098774185","https://openalex.org/W2100401322","https://openalex.org/W2116383462","https://openalex.org/W2116442740","https://openalex.org/W2116774898","https://openalex.org/W2117675763","https://openalex.org/W2119914747","https://openalex.org/W2120070743","https://openalex.org/W2133068870","https://openalex.org/W2137104525","https://openalex.org/W2139394304","https://openalex.org/W2148053762","https://openalex.org/W2181849516","https://openalex.org/W2562989799","https://openalex.org/W2950989964","https://openalex.org/W4205513846","https://openalex.org/W6633543754","https://openalex.org/W6635261211","https://openalex.org/W6637051932","https://openalex.org/W6674884181","https://openalex.org/W6675341372","https://openalex.org/W6677183884","https://openalex.org/W6677555207","https://openalex.org/W6677631742","https://openalex.org/W6677978604","https://openalex.org/W6679958247","https://openalex.org/W6680606377","https://openalex.org/W6685962732","https://openalex.org/W6730904136"],"related_works":["https://openalex.org/W4254851101","https://openalex.org/W3171007296","https://openalex.org/W22115721","https://openalex.org/W2211931904","https://openalex.org/W2065444835","https://openalex.org/W2321234655","https://openalex.org/W2952773340","https://openalex.org/W2470062578","https://openalex.org/W2981861370","https://openalex.org/W2982204590"],"abstract_inverted_index":{"We":[0,68],"present":[1],"a":[2,14,81],"model-free":[3],"method":[4],"for":[5,108],"solving":[6],"the":[7,26,33,54,62,89,96,99,105,119],"Inverse":[8],"Reinforcement":[9],"Learning":[10],"(IRL)":[11],"problem":[12,107],"given":[13],"set":[15],"of":[16,98],"trajectories":[17],"generated":[18,76],"by":[19,32,42,53,77],"different":[20,47,72,109],"experts'":[21,73],"policies.":[22],"In":[23,36],"many":[24,85],"applications,":[25],"observed":[27],"demonstrations":[28,74],"are":[29],"not":[30,59],"produced":[31],"same":[34,55,63],"policy.":[35],"fact,":[37],"they":[38],"may":[39],"be":[40],"provided":[41],"multiple":[43],"experts":[44],"that":[45,57],"follow":[46],"(but":[48],"similar)":[49],"policies":[50,78],"or":[51],"even":[52],"expert":[56],"does":[58],"always":[60],"replicate":[61],"policy":[64],"(e.g.,":[65],"human":[66],"expert).":[67],"propose":[69],"to":[70,102,118],"model":[71],"as":[75],"sampled":[79],"from":[80,84],"distribution.":[82],"Differently":[83],"other":[86],"IRL":[87,120],"approaches,":[88],"proposed":[90],"methodology":[91],"requires":[92],"neither":[93],"knowledge":[94],"about":[95],"dynamics":[97],"system":[100],"nor":[101],"iteratively":[103],"solve":[104],"direct":[106],"candidate":[110],"reward":[111],"functions,":[112],"thus":[113],"providing":[114],"an":[115],"efficient":[116],"solution":[117],"problem.":[121]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}