{"id":"https://openalex.org/W2596874484","doi":"https://doi.org/10.1109/ijcnn.2017.7965896","title":"Deep reward shaping from demonstrations","display_name":"Deep reward shaping from demonstrations","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2596874484","doi":"https://doi.org/10.1109/ijcnn.2017.7965896","mag":"2596874484"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2017.7965896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7965896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10059/2196","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101769265","display_name":"Ahmed Hussein","orcid":"https://orcid.org/0000-0001-5227-9929"},"institutions":[{"id":"https://openalex.org/I522815984","display_name":"Robert Gordon University","ror":"https://ror.org/04f0qj703","country_code":"GB","type":"education","lineage":["https://openalex.org/I522815984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ahmed Hussein","raw_affiliation_strings":["School of Computing Science and Digital, Media Robert Gordon University, Aberdeen, UK"],"affiliations":[{"raw_affiliation_string":"School of Computing Science and Digital, Media Robert Gordon University, Aberdeen, UK","institution_ids":["https://openalex.org/I522815984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040807448","display_name":"Eyad Elyan","orcid":"https://orcid.org/0000-0002-8342-9026"},"institutions":[{"id":"https://openalex.org/I522815984","display_name":"Robert Gordon University","ror":"https://ror.org/04f0qj703","country_code":"GB","type":"education","lineage":["https://openalex.org/I522815984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eyad Elyan","raw_affiliation_strings":["School of Computing Science and Digital, Media Robert Gordon University, Aberdeen, UK"],"affiliations":[{"raw_affiliation_string":"School of Computing Science and Digital, Media Robert Gordon University, Aberdeen, UK","institution_ids":["https://openalex.org/I522815984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016157034","display_name":"Mohamed Medhat Gaber","orcid":"https://orcid.org/0000-0003-0339-4474"},"institutions":[{"id":"https://openalex.org/I12870472","display_name":"Birmingham City University","ror":"https://ror.org/00t67pt25","country_code":"GB","type":"education","lineage":["https://openalex.org/I12870472"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mohamed Medhat Gaber","raw_affiliation_strings":["School of Computing and Digital Technology, Birmingham City University, Birmingham"],"affiliations":[{"raw_affiliation_string":"School of Computing and Digital Technology, Birmingham City University, Birmingham","institution_ids":["https://openalex.org/I12870472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016214321","display_name":"Chrisina Jayne","orcid":"https://orcid.org/0000-0001-7292-2109"},"institutions":[{"id":"https://openalex.org/I522815984","display_name":"Robert Gordon University","ror":"https://ror.org/04f0qj703","country_code":"GB","type":"education","lineage":["https://openalex.org/I522815984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chrisina Jayne","raw_affiliation_strings":["School of Computing Science and Digital, Media Robert Gordon University, Aberdeen, UK"],"affiliations":[{"raw_affiliation_string":"School of Computing Science and Digital, Media Robert Gordon University, Aberdeen, UK","institution_ids":["https://openalex.org/I522815984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101769265"],"corresponding_institution_ids":["https://openalex.org/I522815984"],"apc_list":null,"apc_paid":null,"fwci":1.0373,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.82391735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"510","last_page":"517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9959999918937683,"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":0.8994367122650146},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8139448165893555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7161858677864075},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6480596661567688},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5676810145378113},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.552077054977417},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5066266655921936},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5003540515899658},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.47354406118392944},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.45302245020866394},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4499526619911194},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06811639666557312}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8994367122650146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8139448165893555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7161858677864075},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6480596661567688},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5676810145378113},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.552077054977417},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5066266655921936},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5003540515899658},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.47354406118392944},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.45302245020866394},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4499526619911194},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06811639666557312},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ijcnn.2017.7965896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7965896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:www.open-access.bcu.ac.uk:4140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/IJCNN.2017.7965896","pdf_url":null,"source":{"id":"https://openalex.org/S4306402654","display_name":"BCU Open Access Repository (Birmingham City University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I12870472","host_organization_name":"Birmingham City University","host_organization_lineage":["https://openalex.org/I12870472"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:openair.rgu.ac.uk:10059/2196","is_oa":true,"landing_page_url":"http://hdl.handle.net/10059/2196","pdf_url":null,"source":{"id":"https://openalex.org/S4306400814","display_name":"Open Access Institutional Repository at Robert Gordon University (Robert Gordon University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I522815984","host_organization_name":"Robert Gordon University","host_organization_lineage":["https://openalex.org/I522815984"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference publications"}],"best_oa_location":{"id":"pmh:oai:openair.rgu.ac.uk:10059/2196","is_oa":true,"landing_page_url":"http://hdl.handle.net/10059/2196","pdf_url":null,"source":{"id":"https://openalex.org/S4306400814","display_name":"Open Access Institutional Repository at Robert Gordon University (Robert Gordon University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I522815984","host_organization_name":"Robert Gordon University","host_organization_lineage":["https://openalex.org/I522815984"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference publications"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W158183001","https://openalex.org/W1506176787","https://openalex.org/W1511887321","https://openalex.org/W1757796397","https://openalex.org/W1777239053","https://openalex.org/W1929981607","https://openalex.org/W1949804828","https://openalex.org/W1971890413","https://openalex.org/W1999874108","https://openalex.org/W2038689900","https://openalex.org/W2047425368","https://openalex.org/W2065356613","https://openalex.org/W2082494017","https://openalex.org/W2103254706","https://openalex.org/W2104733512","https://openalex.org/W2106059854","https://openalex.org/W2116165953","https://openalex.org/W2134264591","https://openalex.org/W2135995480","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2151210636","https://openalex.org/W2153027856","https://openalex.org/W2155007355","https://openalex.org/W2156897926","https://openalex.org/W2169209873","https://openalex.org/W2173248099","https://openalex.org/W2198041288","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2397581010","https://openalex.org/W2510924756","https://openalex.org/W2949248709","https://openalex.org/W2962887844","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964164283","https://openalex.org/W4254114958","https://openalex.org/W4298857966","https://openalex.org/W6606436731","https://openalex.org/W6638088447","https://openalex.org/W6675999342","https://openalex.org/W6680105153","https://openalex.org/W6680368475","https://openalex.org/W6682314434","https://openalex.org/W6685331716","https://openalex.org/W6712392314"],"related_works":["https://openalex.org/W2475116013","https://openalex.org/W2770018148","https://openalex.org/W4281658507","https://openalex.org/W4224998860","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,22,114],"learning":[2,20,23,28,40,104],"is":[3,79,139,160,186,225],"rapidly":[4],"gaining":[5],"attention":[6],"due":[7],"to":[8,68,91,109,122,141,149,188,201],"recent":[9],"successes":[10],"in":[11,82,146],"a":[12,26,89,99,118,124,130,181],"variety":[13],"of":[14,18,36,56,175,217],"problems.":[15],"The":[16,54,136,157,204],"combination":[17],"deep":[19,113,131],"and":[21,62,107,111,155,192],"allows":[24],"for":[25,102],"generic":[27],"process":[29],"that":[30,165,185,207],"does":[31],"not":[32],"consider":[33],"specific":[34],"knowledge":[35,174],"the":[37,58,71,76,80,142,176,202,209,215,218,228,230],"task.":[38],"However,":[39],"from":[41,105,117,168],"scratch":[42],"becomes":[43],"more":[44,226],"difficult":[45],"when":[46],"tasks":[47,69,164,179],"involve":[48],"long":[49],"trajectories":[50],"with":[51,75],"delayed":[52,195],"rewards.":[53],"chances":[55],"finding":[57],"rewards":[59,196,212,231],"using":[60,208],"trial":[61,154],"error":[63],"become":[64],"much":[65],"smaller":[66],"compared":[67],"where":[70,193],"agent":[72,219],"continuously":[73],"interacts":[74],"environment.":[77],"This":[78,223],"case":[81],"many":[83,189],"real":[84,190],"life":[85],"applications":[86,191],"which":[87],"poses":[88],"limitation":[90],"current":[92],"methods.":[93],"In":[94],"this":[95],"paper":[96],"we":[97],"propose":[98],"novel":[100],"method":[101,159],"combining":[103],"demonstrations":[106],"experience":[108],"expedite":[110],"improve":[112],"learning.":[115],"Demonstrations":[116],"teacher":[119],"are":[120,166,199],"used":[121,145],"shape":[123],"potential":[125],"reward":[126,143],"function":[127,138,144],"by":[128],"training":[129,152],"supervised":[132],"convolutional":[133],"neural":[134],"network.":[135],"shaped":[137,211],"added":[140],"deep-Q-learning":[147],"(DQN)":[148],"perform":[150],"off-policy":[151],"through":[153],"error.":[156],"proposed":[158,210],"demonstrated":[161],"on":[162],"navigation":[163],"learned":[167],"raw":[169],"pixels":[170],"without":[171],"utilizing":[172],"any":[173],"problem.":[177],"Navigation":[178],"represent":[180],"typical":[182],"AI":[183],"problem":[184],"relevant":[187],"only":[194],"(usually":[197],"terminal)":[198],"available":[200],"agent.":[203],"results":[205],"show":[206],"significantly":[213],"improves":[214],"performance":[216],"over":[220],"standard":[221],"DQN.":[222],"improvement":[224],"pronounced":[227],"sparser":[229],"are.":[232]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}