{"id":"https://openalex.org/W3155473317","doi":"https://doi.org/10.1109/cog52621.2021.9618983","title":"Policy Fusion for Adaptive and Customizable Reinforcement Learning Agents","display_name":"Policy Fusion for Adaptive and Customizable Reinforcement Learning Agents","publication_year":2021,"publication_date":"2021-08-17","ids":{"openalex":"https://openalex.org/W3155473317","doi":"https://doi.org/10.1109/cog52621.2021.9618983","mag":"3155473317"},"language":"en","primary_location":{"id":"doi:10.1109/cog52621.2021.9618983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9618983","pdf_url":null,"source":{"id":"https://openalex.org/S4363608335","display_name":"2021 IEEE Conference on Games (CoG)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Conference on Games (CoG)","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/A5021772177","display_name":"Alessandro Sestini","orcid":"https://orcid.org/0000-0001-5496-5770"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Alessandro Sestini","raw_affiliation_strings":["Dipartimento di Ingegneria dell'Informazione, Universit\u00e0 degli Studi di Firenze, Florence, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria dell'Informazione, Universit\u00e0 degli Studi di Firenze, Florence, Italy","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040529511","display_name":"Alexander Kuhnle","orcid":"https://orcid.org/0000-0002-2361-115X"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alexander Kuhnle","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064029620","display_name":"Andrew D. Bagdanov","orcid":"https://orcid.org/0000-0001-6408-7043"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrew D. Bagdanov","raw_affiliation_strings":["Dipartimento di Ingegneria dell'Informazione, Universit\u00e0 degli Studi di Firenze, Florence, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria dell'Informazione, Universit\u00e0 degli Studi di Firenze, Florence, Italy","institution_ids":["https://openalex.org/I45084792"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021772177"],"corresponding_institution_ids":["https://openalex.org/I45084792"],"apc_list":null,"apc_paid":null,"fwci":0.7613,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73530499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"08"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9966999888420105,"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":0.9606999754905701,"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":0.8335955739021301},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7666730880737305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5662698745727539},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44247323274612427},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.43255022168159485},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39816969633102417}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8335955739021301},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7666730880737305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5662698745727539},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44247323274612427},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.43255022168159485},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39816969633102417},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cog52621.2021.9618983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9618983","pdf_url":null,"source":{"id":"https://openalex.org/S4363608335","display_name":"2021 IEEE Conference on Games (CoG)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},{"id":"pmh:oai:flore.unifi.it:2158/1261561","is_oa":false,"landing_page_url":"http://hdl.handle.net/2158/1261561","pdf_url":null,"source":{"id":"https://openalex.org/S4306402033","display_name":"Florence Research (University of Florence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45084792","host_organization_name":"University of Florence","host_organization_lineage":["https://openalex.org/I45084792"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W168823656","https://openalex.org/W2002305926","https://openalex.org/W2043806097","https://openalex.org/W2061562262","https://openalex.org/W2099471712","https://openalex.org/W2101881799","https://openalex.org/W2150468603","https://openalex.org/W2156578004","https://openalex.org/W2174803659","https://openalex.org/W2460299708","https://openalex.org/W2462906003","https://openalex.org/W2736601468","https://openalex.org/W2891790128","https://openalex.org/W2898191412","https://openalex.org/W2946054758","https://openalex.org/W2962937519","https://openalex.org/W2962943921","https://openalex.org/W2963508354","https://openalex.org/W2964263543","https://openalex.org/W2969284747","https://openalex.org/W2969452868","https://openalex.org/W2975203507","https://openalex.org/W2982316857","https://openalex.org/W2989656431","https://openalex.org/W2994073215","https://openalex.org/W2996037775","https://openalex.org/W2997756832","https://openalex.org/W3011540878","https://openalex.org/W3018036994","https://openalex.org/W3023365787","https://openalex.org/W3029466658","https://openalex.org/W3081310128","https://openalex.org/W3092203123","https://openalex.org/W3093853968","https://openalex.org/W3102089800","https://openalex.org/W3103780890","https://openalex.org/W3112108956","https://openalex.org/W3112950473","https://openalex.org/W3129322645","https://openalex.org/W3147968035","https://openalex.org/W3181074849","https://openalex.org/W3187808158","https://openalex.org/W4287555775","https://openalex.org/W4288348579","https://openalex.org/W4289288058","https://openalex.org/W4320013936","https://openalex.org/W4321392130","https://openalex.org/W6683147119","https://openalex.org/W6685664872","https://openalex.org/W6718836005","https://openalex.org/W6739585900","https://openalex.org/W6741002519","https://openalex.org/W6753960536","https://openalex.org/W6754521519","https://openalex.org/W6755724153","https://openalex.org/W6761908843","https://openalex.org/W6766549211","https://openalex.org/W6767098056","https://openalex.org/W6770218150","https://openalex.org/W6771750343","https://openalex.org/W6772421901","https://openalex.org/W6781808220","https://openalex.org/W6784110522","https://openalex.org/W6785727547","https://openalex.org/W6787290050","https://openalex.org/W6841393079"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4313488044","https://openalex.org/W3209574120","https://openalex.org/W4312192474","https://openalex.org/W4210805261"],"abstract_inverted_index":{"In":[0],"this":[1,75],"article":[2],"we":[3,77],"study":[4],"the":[5,15,40,44],"problem":[6],"of":[7,17],"training":[8],"intelligent":[9,107],"agents":[10,33,108],"using":[11],"Reinforcement":[12,101],"Learning":[13,102],"for":[14,84,149,156],"purpose":[16],"game":[18,53,116,158],"development.":[19],"Unlike":[20],"systems":[21],"built":[22],"to":[23,28,35,58,63,105,120],"replace":[24],"human":[25],"players":[26],"and":[27,42,123,147,160],"achieve":[29],"super-human":[30],"performance,":[31],"our":[32],"aim":[34],"produce":[36],"meaningful":[37,66],"interactions":[38],"with":[39,99,109],"player,":[41],"at":[43],"same":[45],"time":[46],"demonstrate":[47,90],"behavioral":[48,61,111],"traits":[49],"as":[50,113],"desired":[51],"by":[52,115],"designers.":[54,161],"We":[55,88,142],"show":[56],"how":[57,91,150],"combine":[59],"distinct":[60],"policies":[62],"obtain":[64],"a":[65],"\u201cfusion\u201d":[67],"policy":[68,81,136],"which":[69],"comprises":[70],"all":[71,140],"these":[72,92,151],"behaviors.":[73],"To":[74],"end,":[76],"propose":[78],"four":[79],"different":[80,131],"fusion":[82,137],"methods":[83,93,152],"combining":[85],"pre-trained":[86],"policies.":[87],"further":[89],"can":[94],"be":[95],"used":[96],"in":[97,103],"combination":[98],"Inverse":[100],"order":[104],"create":[106],"specific":[110],"styles":[112],"chosen":[114],"designers,":[117],"without":[118],"having":[119],"define":[121],"many":[122],"possibly":[124],"poorly-designed":[125],"reward":[126],"functions.":[127],"Experiments":[128],"on":[129],"two":[130],"environments":[132],"indicate":[133],"that":[134],"entropy-weighted":[135],"significantly":[138],"outperforms":[139],"others.":[141],"provide":[143],"several":[144],"practical":[145],"examples":[146],"use-cases":[148],"are":[153],"indeed":[154],"useful":[155],"video":[157],"production":[159]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2021-04-26T00:00:00"}