{“id”：“https://openalex.org/W2990460121“，”doi“：”https://doi.org/10.3389/fnbot.2019.00103“，”title“：”受限深度Q-Learning逐渐接近普通Q-Learch“，”display_name“：”约束深度Q-Learning逐渐接近普通Q-Learning“，”publication_year“：2019，”publiation_date“：”2019-12-10“，”ids“：{”openalex“：”https://openalex.org/W2990460121网址“，”doi“：”https://doi.org/10.3389/fnbot.2019.00103“，”mag“：”2990460121“，”pmid“：”https://pubmed.ncbi.nlm.nih.gov/31920613“，”pmcid“：”https://www.ncbi.nlm.nih.gov/pmc/articles/6914867“}，”language“：”en“，”primary_location“：{”is_oa“：true，”landing_page_url“：”https://doi.org/10.3389/fnbot.2019.00103，“pdf_url”：https://www.frontiersin.org/articles/10.3389/fnbot.2019.00103/pdf，“源”：{“id”：https://openalex.org/S115606517“，”display_name“：”神经机器人学的前沿“，”issn_l“：”1662-5218“，”isn“：[”1662-51218“]，”is_oa“：true，”is-in_doaj“：true，”is_core“：true，”host_organization“：”https://openalex.org/P4310320527“，”“host_organization_name”：“Frontiers Media”，“host_organization_lineage”：[“https://openalex.org/P4310320527“]，”host_organization_lineage_names“：[”Frontiers Media“]，“type”：“journal”}，“license”：“cc-by”，“licence_id”：“https://openalex.org/licenses/cc-by“，”version“：”publishedVersion“，”is_accepted“：true，”is_published“：true}，”type“：”article“，”type_crossref“：“journal-article”，”indexed_in“：[”crossref“，”doaj“，”publibmed“]，”open_access“：{”is_oa“：true，”oa_status“：”gold“，”oa_url“：”https://www.frontiersin.org/articles/10.3389/fnbot.2019.00103/pdf“，”any_repository_has_fulltext“：true}，”authorships“：[{”author_position“：”第一“，”作者“：{”id“：”https://openalex.org/A5089449433“，”display_name“：”Shota Ohnishi“，”orcid“：null}，”institutions“：[{”id“：”https://openalex.org/I1283155146“，”display_name“：”松下（日本）“，”ror“：”https://ror.org/011tm7n37“，”country_code“：”JP“，”type“：“company”，”lineage“：[”https://openalex.org/I1283155146“]}，{”id“：”https://openalex.org/I22299242“，”display_name“：”京都大学“，”ror“：”https://ror.org/02kpeqv85“，”country_code“：”JP“，”type“：“教育”，”世系“：[”https://openalex.org/I22299242“]}]，”国家“：[”JP“]，”is_corresponding“：false，”raw_author_name“：”Shota Ohnishi“，”raw _affiliation_strings“：[“京都大学信息学研究生院系统科学系，现隶属于日本京都松下有限公司”]，”affiliations“：[{”raw _affiliation_string“：”京都大学信息学研究生院系统科学系，现隶属于日本京都松下株式会社”，“institute_ids”：[https://openalex.org/I1283155146","https://openalex.org/I22299242“]}]}，{”author_position“：”middle“，”author“：{”id“：”https://openalex.org/A5031054137“，”display_name“：”Eiji Uchibe“，”orcid“：”https://orcid.org/0000-0001-7908-0258}，“机构”：[{“id”：https://openalex.org/I4210104143“，”display_name“：”国际高级电信研究所“，”ror“：”https://ror.org/01pe1d703“，”“country_code”“：”JP“，”type“：”facility“，”lineage“：[”https://openalex.org/I4210104143“]}]，”国家“：[”JP“]，”is_corresponding“：true，”raw_author_name“：”Eiji Uchibe“，”raw _ afiliation_strings“：[“ATR计算神经科学实验室，日本京都”]，”affiliations“：[{”raw _affiliation_string“：”ATR计算神经学实验室，日本东京”，“institution_ids”：[“https://openalex.org/I4210104143“]}]}，{”author_position“：”middle“，”author“：{”id“：”https://openalex.org/A5001831596“，”display_name“：”Yotaro Yamaguchi“，”orcid“：null}，”institutions“：[{”id“：”https://openalex.org/I22299242“，”display_name“：”京都大学“，”ror“：”https://ror.org/02kpeqv85“，”country_code“：”JP“，”type“：“教育”，”世系“：[”https://openalex.org/I22299242“]}]，”countries“：[”JP“]，”is_corresponding“：false，”raw_author_name“：”Yotaro Yamaguchi“，”raw_affiliation_strings“：【”日本京都大学信息学研究生院系统科学系“】，”affiliations“：[{”raw_affiliation_string“：”日本京都京都大学信息学院系统科学系”，“机构ID“：[”https://openalex.org/I22299242“]}]}，{”author_position“：”middle“，”author“：{”id“：”https://openalex.org/A5023583630“，”display_name“：”Kosuke Nakanishi“，”orcid“：”https://orcid.org/0000-0002-0078-6942}，“机构”：[{“id”：https://openalex.org/I1283473643“，”display_name“：”本田（日本）“，”ror“：”https://ror.org/03jzay846“，”country_code“：”JP“，”type“：”company“，”沿袭“：[”https://openalex.org/I1283473643“]}]，”国家“：[”JP“]，”is_corresponding“：false，”raw_author_name“：”Kosuke Nakanishi“，”raw_affiliation_strings“：[“本田研发有限公司，日本崎岖”]，”affiliations“：[{”raw_affiliation_string“：”本田研发公司，日本西塔”，“institution_ids”：[“https://openalex.org/I1283473643“]}]}，{”author_position“：”middle“，”author“：{”id“：”https://openalex.org/A5102188905“，”display_name“：”Yuji Yasui“，”orcid“：null}，”institutions“：[{”id“：”https://openalex.org/I1283473643“，”display_name“：”本田（日本）“，”ror“：”https://ror.org/03jzay846“，”country_code“：”JP“，”type“：“company”，”lineage“：[”https://openalex.org/I1283473643“]}]，”国家“：[”JP“]，”is_corresponding“：false，”raw_author_name“：”Yuji Yasui“，”raw _ afiliation_strings“：[“本田研发有限公司，日本崎岖市”]，”affiliations“：[{”raw _affiliation_strong“：”本田研发公司，日本西塔市”，“institution_ids”：[“https://openalex.org/I1283473643“]}]}，{”author_position“：”last“，”author“：{”id“：”https://openalex.org/A5072540019“，”display_name“：”Shin Ishii“，”orcid“：”https://orcid.org/0000-0001-9385-8230}，“机构”：[{“id”：https://openalex.org/I4210104143“，”display_name“：”国际高级电信研究所“，”ror“：”https://ror.org/01pe1d703“，”“country_code”“：”JP“，”type“：”facility“，”lineage“：[”https://openalex.org/I4210104143“]｝，｛”id“：”https://openalex.org/I22299242“，”display_name“：”京都大学“，”ror“：”https://ror.org/02kpeqv85“，”country_code“：”JP“，”type“：“教育”，”世系“：[”https://openalex.org/I22299242“]}]，”国家“：[”JP“]，”is_corresponding“：false，”raw_author_name“：”Shin Ishii“，”raw _affiliation_strings“：[“日本京都ATR计算神经科学实验室”，“日本京都大学信息学研究生院系统科学系”]，“affiliations”：[{“raw_affilition_string”：“ATR计算神经科学实验室，日本京都”，“institution_ids”：[“https://openalex.org/I4210104143“]}，{”raw_affiliation_string“：”日本京都大学信息学研究生院系统科学系“，”institution_ids“：[”https://openalex.org/I22299242“]}]}]，”countries_disticont_count“：1，”institutions_disticent_count”：4，”corresponding_author_ids“：[”https://openalex.org/A5031054137“]，”对应的机构ID“：[”https://openalex.org/I4210104143“]，”apc_list“：{”value“：2950，”currency“：”USD“，”value_USD“：2960，”provenance“：”doaj“}，”apc _payed“：”{“value”：2950；”currentary“：”美元“，”value_USD”：2950.，“provenance”：“doaj”}，“fwci”：3.656，“has_fulltext_origin”：“pdf”，“cited_by_count”：47，“citation_normalized_percentile”：{“值”：0.99994，“is_in_top_1_percent”：真，“is_ in_top_10_percents”：真}，“cited_by_percentle_year“：｛“min”：96，“max”：97｝，“biblio”：｛“volume”：“13”，“issue”：null，“first_page”：null，“last_page”：null｝，“is_retracted”：false，“is_paratext”：false，“primary_topic”：｛“id”：“https://openalex.org/T10057“，”“display_name”：“人脸识别和降维技术”，“score”：0.9907，“subfield”：{“id”：“https://openalex.org/subfields/1707“，”display_name“：”计算机视觉和模式识别“}，”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/T10057“，”“display_name”：“人脸识别和降维技术”，“score”：0.9907，“subfield”：{“id”：“https://openalex.org/subfields/1707“，”display_name“：”计算机视觉和模式识别“}，”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/T11307“，”display_name“：”转移学习和领域适应的进展“，”score“：0.9862，”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“：”物理科学“}}，{”id“：”https://openalex.org/T12676“，”display_name“：”极限学习机器的理论与应用“，”score“：0.9859，”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“：”物理科学“}}]，”关键词“：[{”id“：”https://openalex.org/keywords/q-learning网站“，”display_name“：”Q-learning“，”score“：0.6321305}，{”id“：”https://openalex.org/keywords/transfer-learning网站“，”display_name“：”转移学习“，”score“：0.550145}，{”id“：”https://openalex.org/keywords/semi-supervised-learning网站“，”display_name“：”半监督学习“，”score“：0.549138}，{”id“：”https://openalex.org/keywords/representation-relearning（https://openalex.org/keywords/representation-relearning）“，”display_name“：”表征学习“，”score“：0.54594}，{”id“：”https://openalex.org/keywords/unsupervised学习“，”display_name“：”无监督学习“，”score“：0.532509}，{”id“：”https://openalex.org/keywords/incremental-learning网站“，”display_name“：”增量学习“，”score“：0.53181}]，”concepts“：[{”id“：”https://openalex.org/C41008148，“wikidata”：https://www.wikidata.org/wiki/Q21198“，”display_name“：”计算机科学“，”level“：0，”score“：0.81567794}，{”id“：”https://openalex.org/C188116033，“wikidata”：https://www.wikidata.org/wiki/Q2664563“，”display_name“：”Q-learning“，”level“：3，”score“：0.6321305}，{”id“：”https://openalex.org/C154945302，“wikidata”：https://www.wikidata.org/wiki/Q11660“，”display_name“：”人工智能“，”level“：1，”score“：0.5774919}，{”id“：”https://openalex.org/C108583219，“wikidata”：https://www.wikidata.org/wiki/Q197536“，”display_name“：”深度学习“，”level“：2，”score“：0.5572082}，{”id“：”https://openalex.org/C119857082，“wikidata”：https://www.wikidata.org/wiki/Q2539“，”display_name“：”机器学习“，”level“：1，”score“：0.3921502}，{”id“：”https://openalex.org/C97541855，“wikidata”：https://www.wikidata.org/wiki/Q830687“，”display_name“：”强化学习“，”level“：2，”score“：0.310904}]，”mesh“：[]，”locations_count“：5，”location“：[{”is_oa“：true，”landing_page_url“：”https://doi.org/10.3389/fnbot.2019.00103，“pdf_url”：https://www.frontiersin.org/articles/10.3389/fnbot.2019.00103/pdf，“源”：{“id”：https://openalex.org/S115606517“，”display_name“：”神经机器人学的前沿“，”issn_l“：”1662-5218“，”isn“：[”1662-51218“]，”is_oa“：true，”is-in_doaj“：true，”is_core“：true，”host_organization“：”https://openalex.org/P4310320527“，”“host_organization_name”：“Frontiers Media”，“host_organization_lineage”：[“https://openalex.org/P4310320527“]，”host_organization_lineage_names“：[”Frontiers Media“]，“type”：“journal”}，“license”：“cc-by”，“licence_id”：“https://openalex.org/licenses/cc-by“，”version“：”publishedVersion“，”is_accepted“：true，”is_published“：true}，{”is_oa“：false，”landing_page_url“：”https://doaj.org/article/b93b5b7b16874660b7e0bde3e5ef1057“，”pdf_url“：空，”源“：{”id“：”https://openalex.org/S4306401280“，”display_name“：”DOAJ（DOAJ：开放存取期刊目录）“，”issn_l“：null，”issn“：null:”is_oa“：true，”is_in_DOAJ“：false，”is_core“：false，”host_organization“：null，”host_organization_name“:null，“host_orgganization_lineage”：[]，“host_orgganization _lineage_names”：[[]，”type“：”repository“}”，“license”：nullis_accepted“：false，”is_published“：false}，{“is_oa”：true，”landing_page_url“：”https://europepmc.org/articles/pmc6914867，“pdf_url”：https://europepmc.org/articles/pmc6914867？pdf=render，“源”：{“id”：https://openalex.org/S4306400806“，”display_name“：”Europe PMC（PubMed Central）“，”issn_l“：null，”issn“：null，”is_oa“：true，”is_ in_doaj“：false，”is_core“：false，”host_organization“：”https://openalex.org/I1303153112“，”“host_organization_name”：“欧洲生物信息学研究所”，“host_organization_lineage”：[“https://openalex.org/I1303153112“]，”host_organization_lineage_names“：[”欧洲生物信息学研究所“]，“type”：“repository”}，“license”：“cc-by”，“licence_id”：“https://openalex.org/licenses/cc-by“，”版本“：”已发布版本“，”is_accepted“：true，”is_published“：true｝，｛”is_oa“：true，”landing_page_url“：”https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6914867“，”pdf_url“：空，”源“：{”id“：”https://openalex.org/S2764455111“，”display_name“：”PubMed Central“，”issn_l“：null，”issn“：null，”is_oa“：true，”is_ in_doaj“：false，”is_core“：false，”host_organization“：”https://openalex.org/I1299303238“，”host_organization_name“：”美国国立卫生研究院“，”host_organization_lineage“：[”https://openalex.org/I1299303238“]，”host_organization_lineage_names“：[”National Institutes of Health“]，“type”：“repository”}，“license”：null，“licence_id”：null，“version”：“publishedVersion”，“is_accepted”：true，“is_published”：true}，{“is_oa”：false，“landing_page_url”：“https://pubmed.ncbi.nlm.nih.gov/1920613“，”pdf_url“：空，”源“：{”id“：”https://openalex.org/S4306525036“，”display_name“：”PubMed“，”issn_l“：null，”issn“：null，”is_oa“：false，”is_ in_doaj“：false，”is_core“：false，”host_organization“：”https://openalex.org/I1299303238“，”host_organization_name“：”美国国立卫生研究院“，”host_organization_lineage“：[”https://openalex.org/I1299303238“]，”host_organization_lineage_names“：[”National Institutes of Health“]，“type”：“repository”}，“license”：null，“licence_id”：null，“version”：null，“is_accepted”：false，“is_published”：false}]，“best_oa_location”：{“is_oa”：true，“landing_page_url”：“https://doi.org/10.3389/fnbot.2019.00103，“pdf_url”：https://www.frontiersin.org/articles/10.3389/fnbot.2019.00103/pdf，“源”：{“id”：https://openalex.org/S115606517“，”display_name“：”神经机器人学的前沿“，”issn_l“：”1662-5218“，”isn“：[”1662-51218“]，”is_oa“：true，”is-in_doaj“：true，”is_core“：true，”host_organization“：”https://openalex.org/P4310320527“，”“host_organization_name”：“Frontiers Media”，“host_organization_lineage”：[“https://openalex.org/P4310320527“]，”host_organization_lineage_names“：[”Frontiers Media“]，“type”：“journal”}，“license”：“cc-by”，“licence_id”：“https://openalex.org/licenses/cc-by“，”version“：”publishedVersion“，”is_accepted“：true，”is_published“：true}，”sustainable_development_goals“：[]，”grants“：{”funder“：”https://openalex.org/F4320321034“，”“funder_display_name”：“新能源和工业技术开发组织”，“award_id”：null}，{“funder”：“https://openalex.org/F4320334764“，”“funder_display_name”：“日本科学促进会”，“award_id”：null}]，“datasets”：[]，“versions”：[]，“referenced_works_count”：25，“referrenced_works”：[”https://openalex.org/W1557517019","https://openalex.org/W1583837637","https://openalex.org/W1595483645","https://openalex.org/W1810943226","https://openalex.org/W2139418546","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2508424122","https://openalex.org/W2531563875","https://openalex.org/W2602856279","https://openalex.org/W2766447205","https://openalex.org/W2805560727","https://openalex.org/W2900582619","https://openalex.org/W2907626093","https://openalex.org/W2912496897","https://openalex.org/W2913529121","https://openalex.org/W2952348496","https://openalex.org/W2962847657","https://openalex.org/W2964547635","https://openalex.org/W2990138404","https://openalex.org/W3139610437","https://openalex.org/W32403112","https://openalex.org/W4255430598","https://openalex.org/W4285719527","https://openalex.org/W4298857966“]，”related_works“：[”https://openalex.org/W4360585206","https://openalex.org/W4321369474","https://openalex.org/W4306674287","https://openalex.org/W4285208911","https://openalex.org/W3215138031","https://openalex.org/W3046775127","https://openalex.org/W3009238340","https://openalex.org/W2961085424","https://openalex.org/W2939353110","https://openalex.org/W2731899572“]，”abstract_inverted_index“：{”A“：[0,82]，”deep“：[1,19]，”Q“：[2,13,26,47,70136162204]，”network“：[3,89109141167237]，”（DQN）“：[4]，”（Mnih“：[5]，”et“：[6]，”al.，“：[7]，“2013）”：[8]，”is“：[9,16,37,66,75103110168178226]，“an”：[10,49274]，“extension”：[11]，“of”：[12,86118134160189221234240244]，“learning”，“：[14]，”which“：[15,60]，”a“：[17,25,40,57,62,93115143213241]，”典型“：[18]，”强化“：[20]，”学习“：[21,80,96185]，”方法。“：[22]，”In“：[23,55120180]，”DQN“：[24,56]，”function“：[27,71137163]，”expresses“：[28]，”all“：[29,33]，”action“：[30]，”values“：[31]，”under“：[32]，”states“：[34]，”and“：[35,65138164170223238]，”it“：[36171225]，”approximated“：[38,46]，”using“：[39]，”卷积“：[41]，”神经“：[42]，”网络“：[43]，”使用“：[44]，”派生的“：[45,69,79,87100107129132135146158161165181187192219231235245]，”函数“，：[48]，”最优“：[50]，”策略“：[51]，”可以“：[52270]，”是“：[53271]，”。“：[54]，”目标“：[58,63,88101108140147166236]，”网络“：[59]，”计算“：[61]，”值“：[64102]，”更新“：[67]，”by“：[68]，”at“：[72]，”常规“：[73]，”间隔“：[74]，”引入“：[76]，”to“：[77258277]，”稳定“：[78]，”进程。“：[81,97]，”较少“：[83]，”频繁“：[84]，”更新“：[85151172]，”将“：[90]，”结果“：[91]，”in“：[92218230256]，”more“：[94]，”稳定“：[95]，”然而，“：[98]，”因为“：[99]，”不是“：[104252]，”传播“：[105]，”除非“：[106]，”已更新“：[111]，”DQN“：[111212615021022249269]，”通常“：[113]，”requires“：[114]，”large“：[116]，”number“：[117188]，”samples。“：[119]，”this“：[121176]，”study“：[122]，”we“：[123]，”proposed“：[124182]，”Constrained“：[125149209248268]，”that“：[127191208224267]，”uses“：[128]，”difference“：[130156177]，”between“：[131157]，”outputs“：[133159]，”as“：[142184273]，”constraint“：[144]，”on“：[145]，”value。“：[148]，”parameters“：[152]，”conservatively“：[153]，”when“：[154175]，”large“，”：[169]，”theme“：[173]，”aggressive“：[174]，”small。“：[179]，”方法“：[183]，”进度“：[186]，”时间“：[190]，”约束“：[193]，”是“：[194]，”激活“：[195]，”减少。“：【196】，”因此，“：【197】，”更新“：【199232】，”方法“：【200】，”逐渐“：【201】，”方法“：【202260】，”常规“：【203】，”学习。“：[205]，”We“：[206]，”found“：[207]，”converges“：[211]，”with“：/212]，”smaller“：[214]，”training“：[215]，”dataset“：[216]，”than“：[217]，”case“：[220]，”robust“：[227]，”against“：[228]，”changes“:[229]，”frequency“：[233]，”settings“：/239]，”sequent“：[242]，”parameter“：[243]，”optimizer。“：[246]，”虽然“：[247]，”单独“：[250]，”做“：[251]，”显示“：[253266]，”更好“：[254]，”性能“：[255]，”比较“：[257]，”综合“：[259]，”或“：[261]，”分布式“：[262]，”方法“：[263]，”实验“：[264]，”结果“：[265]，”使用“：[272]，”附加“：[275]，”组件“：[276]，“那些”：[278]，“方法。“：[279]}，”cited_by_api_url“：”https://api.openalex.org/works？filter=cites:W2990460121“，”counts_by_year“：[{”年“：2024，”cited_by_count“：5}，{”年份“：2023，”ciped_by_cunt“：11}，”{“年份”：2022，“cited_by_count”：14}，“{”年度“：2021，”cited_by_count 2“，”创建日期“：”2019-12-05“}