{"id":"https://openalex.org/W4406132533","doi":"https://doi.org/10.1007/s00521-024-10829-4","title":"Do as you teach: a multi-teacher approach to self-play in deep reinforcement learning","display_name":"Do as you teach: a multi-teacher approach to self-play in deep reinforcement learning","publication_year":2025,"publication_date":"2025-01-07","ids":{"openalex":"https://openalex.org/W4406132533","doi":"https://doi.org/10.1007/s00521-024-10829-4"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-024-10829-4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00521-024-10829-4","pdf_url":null,"source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-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/A5084966859","display_name":"Chaitanya Kharyal","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chaitanya Kharyal","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084915709","display_name":"Sai Krishna Gottipati","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sai Krishna Gottipati","raw_affiliation_strings":["AI Redefined Inc, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0003-0251-1851","affiliations":[{"raw_affiliation_string":"AI Redefined Inc, Montreal, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071977537","display_name":"Tanmay Kumar Sinha","orcid":"https://orcid.org/0000-0002-1937-8682"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tanmay Kumar Sinha","raw_affiliation_strings":["Northwestern University, Evanston, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, US","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070172919","display_name":"Fatemeh Abdollahi","orcid":"https://orcid.org/0000-0002-3962-9207"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Fatemeh Abdollahi","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113109052","display_name":"Srijita Das","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130704","display_name":"University of Michigan\u2013Dearborn","ror":"https://ror.org/035wtm547","country_code":"US","type":"education","lineage":["https://openalex.org/I4210130704"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Srijita Das","raw_affiliation_strings":["University of Michigan-Dearborn, Dearborn, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan-Dearborn, Dearborn, US","institution_ids":["https://openalex.org/I4210130704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070914351","display_name":"Matthew E. Taylor","orcid":"https://orcid.org/0000-0001-8946-0211"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Matthew E. Taylor","raw_affiliation_strings":["AI Redefined Inc, Montreal, Canada","University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Redefined Inc, Montreal, Canada","institution_ids":[]},{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5084915709","https://openalex.org/A5113109052"],"corresponding_institution_ids":["https://openalex.org/I4210130704"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":1.2644,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82223896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"37","issue":"8","first_page":"5945","last_page":"5956"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9921000003814697,"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/T10260","display_name":"Software Engineering Research","score":0.9674999713897705,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8823123574256897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7601854801177979},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6057184338569641},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.5721417665481567},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5656383037567139},{"id":"https://openalex.org/keywords/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.5271113514900208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48004424571990967},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4276483356952667},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4265105426311493},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4175068736076355},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.36214423179626465},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35164910554885864},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11109626293182373},{"id":"https://openalex.org/keywords/pedagogy","display_name":"Pedagogy","score":0.08391836285591125},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08341482281684875}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8823123574256897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7601854801177979},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6057184338569641},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.5721417665481567},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5656383037567139},{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.5271113514900208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48004424571990967},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4276483356952667},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4265105426311493},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4175068736076355},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.36214423179626465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35164910554885864},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11109626293182373},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.08391836285591125},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08341482281684875},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00521-024-10829-4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00521-024-10829-4","pdf_url":null,"source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W1542595278","https://openalex.org/W2417786368","https://openalex.org/W2603088459","https://openalex.org/W2616430965","https://openalex.org/W2766447205","https://openalex.org/W2788741142","https://openalex.org/W2895961679","https://openalex.org/W2902855213","https://openalex.org/W2921955147","https://openalex.org/W2963523627","https://openalex.org/W2965621489","https://openalex.org/W2988177603","https://openalex.org/W3019734328","https://openalex.org/W3034296891","https://openalex.org/W3036282537","https://openalex.org/W4221152472","https://openalex.org/W4288029271","https://openalex.org/W4382318696","https://openalex.org/W4401908444","https://openalex.org/W4404738510","https://openalex.org/W4406132533","https://openalex.org/W6602531520","https://openalex.org/W6606637777","https://openalex.org/W6616173779","https://openalex.org/W6629202933","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
