{"id":"https://openalex.org/W2327881649","doi":"https://doi.org/10.1109/devlrn.2014.6982975","title":"Improving reinforcement learning with interactive feedback and affordances","display_name":"Improving reinforcement learning with interactive feedback and affordances","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2327881649","doi":"https://doi.org/10.1109/devlrn.2014.6982975","mag":"2327881649"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2014.6982975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2014.6982975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th International Conference on Development and Learning and on Epigenetic Robotics","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/A5044098673","display_name":"Francisco Cruz","orcid":"https://orcid.org/0000-0002-1131-3382"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Francisco Cruz","raw_affiliation_strings":["Department of Informatics, University of Hamburg, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015567592","display_name":"Sven Magg","orcid":"https://orcid.org/0000-0002-0589-6585"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sven Magg","raw_affiliation_strings":["Department of Informatics, University of Hamburg, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102025003","display_name":"Cornelius Weber","orcid":"https://orcid.org/0000-0001-5163-938X"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cornelius Weber","raw_affiliation_strings":["Department of Informatics, University of Hamburg, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Wermter","raw_affiliation_strings":["Universitat Hamburg, Hamburg, Hamburg, DE"],"affiliations":[{"raw_affiliation_string":"Universitat Hamburg, Hamburg, Hamburg, DE","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044098673"],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":null,"apc_paid":null,"fwci":0.844,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.82941906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"5","issue":null,"first_page":"165","last_page":"170"},"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":0.9990000128746033,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9972000122070312,"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":0.9072679281234741},{"id":"https://openalex.org/keywords/affordance","display_name":"Affordance","score":0.8356119394302368},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8035999536514282},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6114025712013245},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5561578273773193},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5424663424491882},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4889777898788452},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.485227108001709},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.45887553691864014},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4508886933326721},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4303867518901825},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.429917573928833},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34923315048217773},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10212814807891846}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9072679281234741},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.8356119394302368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8035999536514282},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6114025712013245},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5561578273773193},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5424663424491882},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4889777898788452},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.485227108001709},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.45887553691864014},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4508886933326721},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4303867518901825},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.429917573928833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34923315048217773},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10212814807891846},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/devlrn.2014.6982975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2014.6982975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th International Conference on Development and Learning and on Epigenetic Robotics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323458","display_name":"Universidad de Chile","ror":"https://ror.org/047gc3g35"},{"id":"https://openalex.org/F4320334812","display_name":"Comisi\u00f3n Nacional de Investigaci\u00f3n Cient\u00edfica y Tecnol\u00f3gica","ror":"https://ror.org/02ap3w078"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W8222043","https://openalex.org/W197704362","https://openalex.org/W264301034","https://openalex.org/W1506806321","https://openalex.org/W1529399279","https://openalex.org/W1559413237","https://openalex.org/W1569756368","https://openalex.org/W1663973292","https://openalex.org/W1963873191","https://openalex.org/W1966259872","https://openalex.org/W1975550062","https://openalex.org/W1983801113","https://openalex.org/W1999549166","https://openalex.org/W2006292430","https://openalex.org/W2093313552","https://openalex.org/W2098441518","https://openalex.org/W2121863487","https://openalex.org/W2146055337","https://openalex.org/W2155217025","https://openalex.org/W2157174816","https://openalex.org/W2188290233","https://openalex.org/W2324134362","https://openalex.org/W2965916140","https://openalex.org/W3139377883","https://openalex.org/W4211089519","https://openalex.org/W4214717370","https://openalex.org/W6607978175","https://openalex.org/W6631533588","https://openalex.org/W6651641432","https://openalex.org/W6674812091","https://openalex.org/W7017133476","https://openalex.org/W7026514825"],"related_works":["https://openalex.org/W2371091044","https://openalex.org/W87513465","https://openalex.org/W2786230833","https://openalex.org/W2391666574","https://openalex.org/W2352650970","https://openalex.org/W1493952344","https://openalex.org/W4312372616","https://openalex.org/W8539471","https://openalex.org/W1544514152","https://openalex.org/W3203256658"],"abstract_inverted_index":{"Interactive":[0],"reinforcement":[1,11,39,82],"learning":[2,12,40,83],"constitutes":[3],"an":[4,23],"alternative":[5],"for":[6,25],"improving":[7],"convergence":[8,75],"speed":[9,76],"in":[10,28,77],"methods.":[13],"In":[14],"this":[15,59],"work,":[16],"we":[17],"investigate":[18],"inter-agent":[19],"training":[20],"and":[21,41,69,80],"present":[22],"approach":[24,60],"knowledge":[26,45,66],"transfer":[27],"a":[29,33,47],"domestic":[30],"scenario":[31],"where":[32],"first":[34],"agent":[35,49],"is":[36],"trained":[37],"by":[38,50,64],"afterwards":[42],"transfers":[43],"selected":[44],"to":[46,52],"second":[48],"instructions":[51],"achieve":[53],"more":[54],"efficient":[55],"training.":[56],"We":[57],"combine":[58],"with":[61],"action-space":[62],"pruning":[63],"using":[65],"on":[67],"affordances":[68],"show":[70],"that":[71],"it":[72],"significantly":[73],"improves":[74],"both":[78],"classic":[79],"interactive":[81],"scenarios.":[84]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
