｛“id”：“https://openalex.org/W4393324216“，”doi“：”https://doi.org/10.1007/978-3-031-56255-6_3“，”title“：”协作多代理任务中的学习奖励机器“，”display_name“：”合作多代理任务的学习奖励机“，”publication_year“：2024，”publiation_date“：”2024-01-01“，”ids“：{”openalex“：”https://openalex.org/W4393324216“，”doi“：”https://doi.org/10.1007/978-3-031-56255-6_3“}，”language“：”en“，”primary_location“：{”is_oa“：false，”landing_page_url“：”https://doi.org/10.1007/978-3-031-56255-6_3“，”pdf_url“：空，”源“：{”id“：”https://openalex.org/S106296714“，”display_name“：”计算机科学讲义“，”issn_l“：”0302-9743“，”isn“：[”0302-7743“、”1611-3349“]，”is_oa“：false、”is_in_doaj“：false、”is_core“：true、”host_organization“：”https://openalex.org/P4310318900“，”“host_organization_name”：“Springer Science+Business Media”，“host_organization_lineage”：[“https://openalex.org/P4310319965","https://openalex.org/P4310318900“]，”host_organization_lineage_names“：[”Springer Nature“，”Springer-Science+Business Media“]，“type”：“book-series”}，“license”：null，“licence_id”：nul，“version”：null，“is_accepted”：false，“is_published”：false}，”type“：”book-chapter“，”type_crossref“：“book-chapter”，”indexed_in“：[“crossref”]，”open_access“：{”is_oa“：false”“，”oa_url“：空，”any_repository_has_fulltext“：false}，”作者身份“：[{”作者位置“：”第一个“，”作者“：{”id“：”https://openalex.org/A5047729153“，”display_name“：”Leo Ardon“，”orcid“：”https://orcid.org/0000-0003-4400-7127“｝，”机构“：[｛”id“：”https://openalex.org/I47508984“，”display_name“：”伦敦帝国理工学院“，”ror“：”https://ror.org/041kmwe10“，”country_code“：”GB“，”type“：“教育”，”世系“：[”https://openalex.org/I47508984“]}]，”国家“：[”GB“]，”is_corresponding“：true，”raw_author_name“：”Leo Ardon“，”raw _affiliation_strings“：[“英国伦敦帝国理工学院”]，”从属关系“：[{”raw _affiliation_string“：”英国伦敦帝国学院”，“institution_ids”：[“https://openalex.org/I47508984“]}]}，{”author_position“：”middle“，”author“：{”id“：”https://openalex.org/A5023452296“，”display_name“：”Daniel Furelos-Blanco“，”orcid“：”https://orcid.org/0000-0001-7461-1910“｝，”机构“：[｛”id“：”https://openalex.org/I47508984“，”display_name“：”伦敦帝国理工学院“，”ror“：”https://ror.org/041kmwe10“，”country_code“：”GB“，”type“：“教育”，”世系“：[”https://openalex.org/I47508984“]}]，”countries“：[”GB“]，”is_corresponding“：false，”raw_author_name“：”Daniel Furelos-Blanco“，”raw _ afiliation_strings“：【”英国伦敦帝国理工学院“】，”affiliations“：[{”raw _affiliation_strong“：”英国伦敦皇家理工学院”，“institution_ids”：[”https://openalex.org/I47508984“]}]}，{”author_position“：”last“，”author“：{”id“：”https://openalex.org/A5046462940“，”display_name“：”Alessandra Russo“，”orcid“：”https://orcid.org/0000-0002-3318-8711“｝，”机构“：[｛”id“：”https://openalex.org/I47508984“，”display_name“：”伦敦帝国理工学院“，”ror“：”https://ror.org/041kmwe10“，”country_code“：”GB“，”type“：“教育”，”世系“：[”https://openalex.org/I47508984“]}]，”countries“：[”GB“]，”is_corresponding“：false，”raw_author_name“：”Alessandra Russo“，”raw _ afiliation_strings“：【”英国伦敦帝国理工学院“】，”affiliations“：[{”raw_ afiliation _string“：”英国伦敦皇家理工学院”，“institution_ids”：[“https://openalex.org/I47508984“]}]}]，”countries_disticont_count“：1，”institutions_disticent_count”：1，“corresponding_author_ids”：[“https://openalex.org/A5047729153“]，”对应的机构ID“：[”https://openalex.org/I47508984“]，”apc_list“：{”value“：5000，”currency“：”EUR“，”value_usd“：5392，”provenance“：”doaj“}，”apc _payed“：null，”fwci“：null，”has_fulltext“：false，”cited_by_count“：0，”cited_by_percentile_year“：{“min”：0，“max”：90}，“biblio”：{“volume”：null、“issue”：null、“first_page”：“43”、“last_page”：“59”}，“is_retracted”：false，“is_paratext”：false，“primary_topic”：{“id”：https://openalex.org/T10462“，”display_name“：”强化学习算法“，”score“：0.9993，”subfield“：{”id“：”https://openalex.org/subfields/s702“，”display_name“：”人工智能“}，”字段“：{”id“：”https://openalex.org/fields/17“，”display_name“：”Computer Science“}，”domain“：{”id“：”https://openalex.org/domains/3“，”display_name“：”物理科学“}}，”主题“：[{”id“：”https://openalex.org/T10462“，”display_name“：”强化学习算法“，”score“：0.9993，”subfield“：{”id“：”https://openalex.org/subfields/s702“，”display_name“：”人工智能“}，”字段“：{”id“：”https://openalex.org/fields/17“，”display_name“：”Computer Science“}，”domain“：{”id“：”https://openalex.org/domains/3“，”display_name“：”物理科学“}}，{”id“：”https://openalex.org/T12072“，”“display_name”：“机器学习研究中的主动学习”，“score”：0.9912，“subfield”：{“id”：“https://openalex.org/subfields/s702“，”display_name“：”人工智能“}，”字段“：{”id“：”https://openalex.org/fields/17“，”display_name“：”Computer Science“}，”domain“：{”id“：”https://openalex.org/domains/3“，”display_name“：”物理科学“}}，{”id“：”https://openalex.org/T10820“，”display_name“：”Type-2 Fuzzy Logic Systems and Applications“，”score“：0.9883，”subfield“：｛”id“：”https://openalex.org/subfields/s702“，”display_name“：”人工智能“}，”字段“：{”id“：”https://openalex.org/fields/17“，”display_name“：”Computer Science“}，”domain“：{”id“：”https://openalex.org/domains/3“，”display_name“：”Physical Sciences“｝｝]，”keywords“：[]，”concepts“：[｛”id“：”https://openalex.org/C41008148，“wikidata”：https://www.wikidata.org/wiki/Q21198“，”display_name“：”计算机科学“，”level“：0，”score“：0.88091147}，{”id“：”https://openalex.org/C154945302，“wikidata”：https://www.wikidata.org/wiki/Q11660“，”display_name“：”人工智能“，”level“：1，”score“：0.50527245}，{”id“：”https://openalex.org/C107457646，“wikidata”：https://www.wikidata.org/wiki/Q207434网址“，”display_name“：”Human\u2013computer interaction“，”level“：1，”score“：0.34520662｝]，”mesh“：[]，”locations_count“：1，”locations“：[｛”is_oa“：false，”landing_page_url“：”https://doi.org/10.1007/978-3-031-56255-6_3“，”pdf_url“：空，”源“：{”id“：”https://openalex.org/S106296714“，”display_name“：”计算机科学讲义“，”issn_l“：”0302-9743“，”isn“：[”0302-7743“、”1611-3349“]，”is_oa“：false、”is_in_doaj“：false、”is_core“：true、”host_organization“：”https://openalex.org/P4310318900“，”“host_organization_name”：“Springer Science+Business Media”，“host_organization_lineage”：[“https://openalex.org/P4310319965","https://openalex.org/P4310318900“]，”host_organization_lineage_names“：[”Springer Nature“，”Springer-Science+Business Media“]，“type”：“book series”}，“license”：null，“licence_id”：null，“version”：null，“is_accepted”：false，“is_published”：false}]，“best_oa_location”：nul，“sustainable_development_goals”：[]，“grants”：[]，“dataset”：[]]，“versions”：[】，“referenced_works_count”：19，“referenced_works“：[”https://openalex.org/W2013202293","https://openalex.org/W2017603160","https://openalex.org/W2099618002","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W228104253","https://openalex.org/W2966537673","https://openalex.org/W2972500268","https://openalex.org/W2997022832","https://openalex.org/W3080730120","https://openalex.org/W3092156990","https://openalex.org/W3135068795","https://openalex.org/W3139531864","https://openalex.org/W3175871729","https://openalex.org/W3205386888","https://openalex.org/W3206976301","https://openalex.org/W4214717370网址","https://openalex.org/W4285602641","https://openalex.org/W4327652993“]，”related_works“：[”https://openalex.org/W4391913857","https://openalex.org/W2748952813","https://openalex.org/W2530322880","https://openalex.org/W2478288626","https://openalex.org/W2390279801","https://openalex.org/W2382290278","https://openalex.org/W2376932109","https://openalex.org/W2358668433","https://openalex.org/W2350741829","https://openalex.org/W2001405890“]，”ngrams_url“：”https://api.openalex.org/works/W4393324216/ngrams（英文）“，”“abstract_inverted_index”：{“This”：[0]，“paper”：[1]，“presents”：[2]，“a”：[3,56,68,82,86,95113]，“novel”：[4]，“approach”：[1511]，“to”：[6,54,74]，“Multi-Agent”：[7]，“Recentration”：[8]，“Learning”：[9]，“（MARL）”：[10]，“that”：[1109]，“combines”：[12]，“cooperational”：[13,57,96120]，“任务“：[14]，”分解“：[15]，”使用“：[16,34,62]，”“：[17,24,27,35,39,47,50,63,76,92]，“学习”：[18]，“的”：[19,26,38,49,78,94]，“奖励”：[20]，“机器”：[21]，“（RM）”：[22]，“编码”：[23]，“结构”：[25]，“子任务”。“：[28]，”The“：[29,59106]，”proposed“：[30]，”method“：[31]，”helps“：[32]，”deal“：[33]，”non-Markovian“：[36]，”nature“：[37]，”rewards“：[40]，”in“：[41,67,81119123]，”partial“：[42126]，”observable“：[43127]，”environments“：%44]，”and“：[45,71125]，”improviders“：[46]，”interpretability“：[48]，”learned“：[51,66]，“策略”：[52]，“必需”：[53]，“完成”：[55]，“任务”。“：[58]，“RM”：[60]，“关联”：[61]，“子任务”：[64]，“是”：[65]，“分散”：[69]，“方式”：[70]，“然后”：[72]，“使用”：[73]，“指南”：[75]，“行为”：[77]，“每个”：[79]，“代理”：[80]，“团队”：[83]，“行动”：[84]，“朝向”：[85]，“共同”：[87]，“目标”。“：[88]，”By“：[89]，”doing“：[90]，”so“：[91]，”complexity“：[93]，”multi-agent“：[97]，”problem“：[98]，”is“：[99112]，”reduced“，：[100]，”allowing“：[101]，”for“：[102116]，”more“：[103]，”effectived“：[104]，”learning“。“：[105]，”结果“：[107]，”建议“：[108]，”我们的“：[110]，”有希望“：[114]，”方向“：[115]，”未来“：[117]，”研究“：[118]，”MARL，“：[121]，”特别是“：[122]，”复杂“：[124]，”环境。“：[128]}，”cited_by_api_url“：”https://api.openalex.org/works？filter=cites:W4393324216“，”counts_by_year“：[]，”updated_date“：”2024-06-25T03:05:35.225093“，”created_date:“2024-03-30”}“