{"id":"https://openalex.org/W3015592223","doi":"https://doi.org/10.1109/icpr48806.2021.9412807","title":"Learning from Learners: Adapting Reinforcement Learning Agents to be Competitive in a Card Game","display_name":"Learning from Learners: Adapting Reinforcement Learning Agents to be Competitive in a Card Game","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3015592223","doi":"https://doi.org/10.1109/icpr48806.2021.9412807","mag":"3015592223"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412807","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.04000","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073057205","display_name":"Pablo Barros","orcid":"https://orcid.org/0000-0002-6517-682X"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Pablo Barros","raw_affiliation_strings":["Cognitive Architecture for Collaborative Technologies(CONTACT) Unit, Istituto Italiano di Tecnologia, Genova, Italy","Cognitive Architecture for Collaborative Technologies (CONTACT) Unit, Istituto Italiano di Tecnologia, Genova, Italy"],"affiliations":[{"raw_affiliation_string":"Cognitive Architecture for Collaborative Technologies(CONTACT) Unit, Istituto Italiano di Tecnologia, Genova, Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Cognitive Architecture for Collaborative Technologies (CONTACT) Unit, Istituto Italiano di Tecnologia, Genova, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090811473","display_name":"Ana Tanevska","orcid":"https://orcid.org/0000-0002-2628-4123"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ana Tanevska","raw_affiliation_strings":["Cognitive Architecture for Collaborative Technologies(CONTACT) Unit, Istituto Italiano di Tecnologia, Genova, Italy","Cognitive Architecture for Collaborative Technologies (CONTACT) Unit, Istituto Italiano di Tecnologia, Genova, Italy"],"affiliations":[{"raw_affiliation_string":"Cognitive Architecture for Collaborative Technologies(CONTACT) Unit, Istituto Italiano di Tecnologia, Genova, Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Cognitive Architecture for Collaborative Technologies (CONTACT) Unit, Istituto Italiano di Tecnologia, Genova, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019426146","display_name":"Alessandra Sciutti","orcid":"https://orcid.org/0000-0002-1056-3398"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandra Sciutti","raw_affiliation_strings":["Cognitive Architecture for Collaborative Technologies(CONTACT) Unit, Istituto Italiano di Tecnologia, Genova, Italy","[Istituto Italiano di Tecnologia]"],"affiliations":[{"raw_affiliation_string":"Cognitive Architecture for Collaborative Technologies(CONTACT) Unit, Istituto Italiano di Tecnologia, Genova, Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"[Istituto Italiano di Tecnologia]","institution_ids":["https://openalex.org/I30771326"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073057205"],"corresponding_institution_ids":["https://openalex.org/I30771326"],"apc_list":null,"apc_paid":null,"fwci":0.699,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.74819581,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2716","last_page":"2723"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9955999851226807,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9908000230789185,"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":0.8172062039375305},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7006980180740356},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6138796210289001},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.46929246187210083},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.4518640637397766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4193165600299835},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.410403847694397},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1051948070526123}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8172062039375305},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7006980180740356},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6138796210289001},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.46929246187210083},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4518640637397766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4193165600299835},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.410403847694397},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1051948070526123},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412807","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.04000","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.04000","pdf_url":"https://arxiv.org/pdf/2004.04000","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3015592223","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2004.04000","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2004.04000","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.04000","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.04000","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.04000","pdf_url":"https://arxiv.org/pdf/2004.04000","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3015592223.pdf","grobid_xml":"https://content.openalex.org/works/W3015592223.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W2095487261","https://openalex.org/W2103561211","https://openalex.org/W2155968351","https://openalex.org/W2167489871","https://openalex.org/W2189149359","https://openalex.org/W2583993537","https://openalex.org/W2726005894","https://openalex.org/W2736601468","https://openalex.org/W2762117857","https://openalex.org/W2768629321","https://openalex.org/W2772589676","https://openalex.org/W2795776994","https://openalex.org/W2800093463","https://openalex.org/W2809208194","https://openalex.org/W2890489029","https://openalex.org/W2907953482","https://openalex.org/W2908741085","https://openalex.org/W2910367420","https://openalex.org/W2941072206","https://openalex.org/W2949317487","https://openalex.org/W2962938178","https://openalex.org/W2963376229","https://openalex.org/W2963625099","https://openalex.org/W2963658727","https://openalex.org/W2964043796","https://openalex.org/W2965771985","https://openalex.org/W2967818432","https://openalex.org/W2981038142","https://openalex.org/W3003922374","https://openalex.org/W3007091801","https://openalex.org/W3007681660","https://openalex.org/W3012239466","https://openalex.org/W3098465353","https://openalex.org/W3100944043","https://openalex.org/W6675356487","https://openalex.org/W6677939520","https://openalex.org/W6687141316","https://openalex.org/W6692846177","https://openalex.org/W6748645729","https://openalex.org/W6754988783"],"related_works":["https://openalex.org/W3161477861","https://openalex.org/W2890642430","https://openalex.org/W3029466658","https://openalex.org/W1584210162","https://openalex.org/W3171853008","https://openalex.org/W2110232929","https://openalex.org/W2946669606","https://openalex.org/W1247499718","https://openalex.org/W6705875","https://openalex.org/W1520863891","https://openalex.org/W3107227009","https://openalex.org/W3183955832","https://openalex.org/W2987421469","https://openalex.org/W1975744985","https://openalex.org/W2995453501","https://openalex.org/W2744008828","https://openalex.org/W1848800237","https://openalex.org/W3147364449","https://openalex.org/W1552226771","https://openalex.org/W2990984513"],"abstract_inverted_index":{"Learning":[0],"how":[1,45,84,93,104],"to":[2,4,18,55,58,82,88,96],"adapt":[3,95],"complex":[5],"and":[6,53,57,73,91,115],"dynamic":[7],"environments":[8],"is":[9,27],"one":[10],"of":[11,63,107],"the":[12,77,85,105],"most":[13],"important":[14],"factors":[15],"that":[16],"contribute":[17],"our":[19],"intelligence.":[20],"Endowing":[21],"artificial":[22],"agents":[23,86],"with":[24],"this":[25,37,123],"ability":[26],"not":[28],"a":[29,41,60,64,117],"simple":[30],"task,":[31],"particularly":[32],"in":[33,80],"competitive":[34,65,90],"scenarios.":[35],"In":[36],"paper,":[38],"we":[39,102],"present":[40],"broad":[42],"study":[43],"on":[44,122],"popular":[46],"reinforcement":[47],"learning":[48,78,113],"algorithms":[49],"can":[50],"be":[51,89],"adapted":[52],"implemented":[54],"learn":[56,87],"play":[59],"real-world":[61],"implementation":[62],"multiplayer":[66],"card":[67],"game.":[68],"We":[69],"propose":[70],"specific":[71],"training":[72],"validation":[74],"routines":[75],"for":[76,119],"agents,":[79],"order":[81],"evaluate":[83],"explain":[92],"they":[94],"each":[97,108],"others'":[98],"playing":[99],"style.":[100],"Finally,":[101],"pinpoint":[103],"behavior":[106],"agent":[109],"derives":[110],"from":[111],"their":[112],"style":[114],"create":[116],"baseline":[118],"future":[120],"research":[121],"scenario.":[124]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}