{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T03:21:59Z","timestamp":1775186519866,"version":"3.50.1"},"reference-count":48,"publisher":"Association for Computing Machinery (ACM)","issue":"9","license":[{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Science and Technology Innovation Key R & D Program of Chongqing","award":["CSTB2023TIAD-STX0031"],"award-info":[{"award-number":["CSTB2023TIAD-STX0031"]}]},{"name":"Chinese Academy of Sciences \u201cLight of West China\u201d Program, in part by the Key Cooperation Project of Chongqing Municipal Education Commission","award":["HZ2021008"],"award-info":[{"award-number":["HZ2021008"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2024,11,30]]},"abstract":"<jats:p>\n            It is a longstanding problem that Q-learning suffers from the overestimation bias. This issue originates from the fact that Q-learning uses the expectation of maximum Q-value to approximate the maximum expected Q-value. A number of algorithms, such as Double Q-learning, were proposed to address this problem by reducing the estimation of maximum Q-value, but this may lead to an underestimation bias. Note that this underestimation bias may have a larger performance penalty than the overestimation bias. Different from previous algorithms, this article studies this issue from a fresh perspective, i.e., meta-learning view, which leads to our Meta-Debias Q-learning. The main idea is to extract the maximum expected Q-value with meta-learning over multiple tasks to remove the estimation bias of maximum Q-value and help the agent choose the optimal action more accurately. However, there are two challenges:\n            <jats:italic>(1) How to automatically select suitable training tasks? (2) How to positively transfer the meta-knowledge from selected tasks to remove the estimation bias of maximum Q-value?<\/jats:italic>\n            To address the two challenges mentioned above, we quantify the similarity between the training tasks and the test task. This similarity enables us to select appropriate \u201cpartial\u201d training tasks and helps the agent extract the maximum expected Q-value to remove the estimation bias. Extensive experiment results show that our Meta-Debias Q-learning outperforms SOTA baselines drastically in three evaluation indicators, i.e., maximum Q-value, policy, and reward. More specifically, our Meta-Debias Q-learning only underestimates\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(1.2*10^{-3}\\)<\/jats:tex-math>\n            <\/jats:inline-formula>\n            than the maximum expected Q-value in the multi-armed bandit environment and only differs\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(5.04\\%-5\\%=0.04\\%\\)<\/jats:tex-math>\n            <\/jats:inline-formula>\n            than the optimal policy in the two states MDP environment. In addition, we compare the uniform weight and our similarity weight. Experiment results reveal fundamental insights into why our proposed algorithm outperforms in the maximum Q-value, policy, and reward.\n          <\/jats:p>","DOI":"10.1145\/3688849","type":"journal-article","created":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T15:11:47Z","timestamp":1723648307000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A Meta-Learning Approach to Mitigating the Estimation Bias of Q-Learning"],"prefix":"10.1145","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1083-8769","authenticated-orcid":false,"given":"Tao","family":"Tan","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China and State Key Laboratory of Cognitive Intelligence, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7935-7210","authenticated-orcid":false,"given":"Hong","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China and State Key Laboratory of Cognitive Intelligence, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4267-7795","authenticated-orcid":false,"given":"Xiaoyu","family":"Shi","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7024-2270","authenticated-orcid":false,"given":"Mingsheng","family":"Shang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,12]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"176","volume-title":"Proceedings of the International Conference on Machine Learning.","author":"Anschel Oron","year":"2017","unstructured":"Oron Anschel, Nir Baram, and Nahum Shimkin. 2017. Averaged-DQN: Variance reduction and stabilization for deep reinforcement learning. In Proceedings of the International Conference on Machine Learning. PMLR, 176\u2013185."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1995.478953"},{"key":"e_1_3_2_4_2","first-page":"803","volume-title":"Proceedings of the IEEE International Joint Conference on Neural Networks","volume":"2","author":"Carroll James L.","year":"2005","unstructured":"James L. Carroll and Kevin Seppi. 2005. Task similarity measures for transfer in reinforcement learning task libraries. In Proceedings of the IEEE International Joint Conference on Neural Networks, Vol. 2, IEEE, 803\u2013808."},{"key":"e_1_3_2_5_2","first-page":"6971","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"37","author":"Cetin Edoardo","year":"2023","unstructured":"Edoardo Cetin and Oya Celiktutan. 2023. Learning Pessimism for Reinforcement Learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, 6971\u20136979."},{"key":"e_1_3_2_6_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Chen Xinyue","year":"2021","unstructured":"Xinyue Chen, Che Wang, Zijian Zhou, and Keith W. Ross. 2021. Randomized ensembled double Q-learning: Learning fast without a model. In Proceedings of the International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=AY8zfZm0tDd"},{"key":"e_1_3_2_7_2","first-page":"1032","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Eramo Carlo D.","year":"2016","unstructured":"Carlo D. Eramo, Marcello Restelli, and Alessandro Nuara. 2016. Estimating maximum expected value through gaussian approximation. In Proceedings of the International Conference on Machine Learning. PMLR, 1032\u20131040."},{"key":"e_1_3_2_8_2","first-page":"1125","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Dai Bo","year":"2018","unstructured":"Bo Dai, Albert Shaw, Lihong Li, Lin Xiao, Niao He, Zhen Liu, Jianshu Chen, and Le Song. 2018. Sbeed: Convergent reinforcement learning with nonlinear function approximation. In Proceedings of the International Conference on Machine Learning. PMLR, 1125\u20131134."},{"issue":"2","key":"e_1_3_2_9_2","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1017\/S0004972712001098","article-title":"Some reverses of the Jensen inequality with applications","volume":"87","author":"Dragomir Sever Silvestru","year":"2013","unstructured":"Sever Silvestru Dragomir. 2013. Some reverses of the Jensen inequality with applications. Bulletin of the Australian Mathematical Society 87, 2 (2013), 177\u2013194.","journal-title":"Bulletin of the Australian Mathematical Society"},{"key":"e_1_3_2_10_2","unstructured":"Yan Duan John Schulman Xi Chen Peter L. Bartlett Ilya Sutskever and Pieter Abbeel. 2016. RL2: Fast reinforcement learning via slow reinforcement learning. arXiv:1611.02779. Retrieved from https:\/\/arxiv.org\/pdf\/1611.02779"},{"key":"e_1_3_2_11_2","first-page":"8665","volume-title":"Proceedings of the International Conference on Machine Learning.","author":"Shar Ibrahim El","year":"2020","unstructured":"Ibrahim El Shar and Daniel Jiang. 2020. Lookahead-bounded q-learning. In Proceedings of the International Conference on Machine Learning. PMLR, 8665\u20138675."},{"key":"e_1_3_2_12_2","unstructured":"Rasool Fakoor Pratik Chaudhari Stefano Soatto and Alexander J Smola. 2019. Meta-q-learning. arXiv:1910.00125. Retrieved from https:\/\/arxiv.org\/pdf\/1910.00125"},{"key":"e_1_3_2_13_2","first-page":"1126","volume-title":"Proceedings of the International Conference on Machine Learning.","author":"Finn Chelsea","year":"2017","unstructured":"Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In Proceedings of the International Conference on Machine Learning. PMLR, 1126\u20131135."},{"key":"e_1_3_2_14_2","first-page":"3750","volume-title":"Proceedings of the 32nd International Joint Conference on Artificial Intelligence","author":"Gong Xiaoyu","year":"2023","unstructured":"Xiaoyu Gong, Shuai L\u00fc, Jiayu Yu, Sheng Zhu, and Zongze Li. 2023. Adaptive estimation Q-learning with uncertainty and familiarity. In Proceedings of the 32nd International Joint Conference on Artificial Intelligence, 3750\u20133758."},{"key":"e_1_3_2_15_2","first-page":"2613","article-title":"Double Q-learning","volume":"23","author":"Hasselt Hado","year":"2010","unstructured":"Hado Hasselt. 2010. Double Q-learning. Advances in Neural Information Processing Systems 23 (2010), 2613\u20132621.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_16_2","first-page":"2580","article-title":"Double gumbel q-learning","volume":"36","author":"Hui David Yu-Tung","year":"2024","unstructured":"David Yu-Tung Hui, Aaron C. Courville, and Pierre-Luc Bacon. 2024. Double gumbel q-learning. Advances in Neural Information Processing Systems 36 (2024), 2580\u20132616.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"e_1_3_2_17_2","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1080\/02331888508801827","article-title":"Non-existence of unbiased estimators of ordered parameters","volume":"16","author":"D. Bhaeiyal Ishwaei","year":"1985","unstructured":"Bhaeiyal Ishwaei D., Divakar Shabma, and K. Krishnamoorthy. 1985. Non-existence of unbiased estimators of ordered parameters. Statistics: A Journal of Theoretical and Applied Statistics 16, 1 (1985), 89\u201395.","journal-title":"Statistics: A Journal of Theoretical and Applied Statistics"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.5555\/3586589.3586743"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-040220-090158"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.104021"},{"key":"e_1_3_2_21_2","first-page":"996","article-title":"Finite-sample convergence rates for Q-learning and indirect algorithms","volume":"11","author":"Kearns Michael","year":"1999","unstructured":"Michael Kearns and Satinder Singh. 1999. Finite-sample convergence rates for Q-learning and indirect algorithms. Advances in Neural Information Processing Systems 11 (1999), 996\u20131002.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_22_2","first-page":"15696","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"37","author":"Kondrup Flemming","year":"2023","unstructured":"Flemming Kondrup, Thomas Jiralerspong, Elaine Lau, Nathan de Lara, Jacob Shkrob, My Duc Tran, Doina Precup, and Sumana Basu. 2023. Towards safe mechanical ventilation treatment using deep offline reinforcement learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, 15696\u201315702."},{"key":"e_1_3_2_23_2","volume-title":"International Conference on Learning Representations","author":"Lan Qingfeng","year":"2020","unstructured":"Qingfeng Lan, Yangchen Pan, Alona Fyshe, and Martha White. 2020. Maxmin Q-learning: Controlling the estimation bias of q-learning. In International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=Bkg0u3Etwr"},{"key":"e_1_3_2_24_2","first-page":"93","volume-title":"Proceedings of the IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL).","author":"Lee Donghun","year":"2013","unstructured":"Donghun Lee, Boris Defourny, and Warren B. Powell. 2013. Bias-Corrected Q-learning to control max-operator bias in q-learning. In Proceedings of the IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL). IEEE, 93\u201399."},{"issue":"10","key":"e_1_3_2_25_2","doi-asserted-by":"crossref","first-page":"4011","DOI":"10.1109\/TAC.2019.2912443","article-title":"Bias-corrected Q-learning with multistate extension","volume":"64","author":"Lee Donghun","year":"2019","unstructured":"Donghun Lee and Warren B. Powell. 2019. Bias-corrected Q-learning with multistate extension. IEEE Transactions on Automatic Control 64, 10 (2019), 4011\u20134023.","journal-title":"IEEE Transactions on Automatic Control"},{"key":"e_1_3_2_26_2","first-page":"310","volume-title":"Proceedings of the 13th International Conference on International Conference on Machine Learning (ICML)","volume":"96","author":"Littman Michael L.","year":"1996","unstructured":"Michael L. Littman and Csaba Szepesv\u00e1ri. 1996. A generalized reinforcement-learning model: Convergence and applications. In Proceedings of the 13th International Conference on International Conference on Machine Learning (ICML), Vol. 96, Citeseer, 310\u2013318."},{"key":"e_1_3_2_27_2","volume-title":"Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI)","author":"Liu Yongshuai","year":"2021","unstructured":"Yongshuai Liu, Avishai Halev, and Xin Liu. 2021. Policy learning with constraints in model-free reinforcement learning: A survey. In Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI)."},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2022.119392"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1060.0614"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"issue":"1","key":"e_1_3_2_31_2","doi-asserted-by":"crossref","first-page":"36","DOI":"10.4236\/jilsa.2023.151003","article-title":"A comparison of ppo, td3 and sac reinforcement algorithms for quadruped walking gait generation","volume":"15","author":"Mock James W.","year":"2023","unstructured":"James W. Mock and Suresh S. Muknahallipatna. 2023. A comparison of ppo, td3 and sac reinforcement algorithms for quadruped walking gait generation. Journal of Intelligent Learning Systems and Applications 15, 1 (2023), 36\u201356.","journal-title":"Journal of Intelligent Learning Systems and Applications"},{"key":"e_1_3_2_32_2","unstructured":"Alex Nichol Joshua Achiam and John Schulman. 2018. On first-order meta-learning algorithms. arXiv:1803.02999. Retrieved from https:\/\/arxiv.org\/pdf\/1803.02999"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_3_2_34_2","first-page":"8454","volume-title":"International Conference on Machine Learning","author":"Peer Oren","year":"2021","unstructured":"Oren Peer, Chen Tessler, Nadav Merlis, and Ron Meir. 2021. Ensemble bootstrapping for q-learning. In International Conference on Machine Learning. PMLR, 8454\u20138463."},{"key":"e_1_3_2_36_2","first-page":"5331","volume-title":"International Conference on Machine Learning","author":"Rakelly Kate","year":"2019","unstructured":"Kate Rakelly, Aurick Zhou, Chelsea Finn, Sergey Levine, and Deirdre Quillen. 2019. Efficient off-policy meta-reinforcement learning via probabilistic context variables. In International Conference on Machine Learning. PMLR, 5331\u20135340."},{"key":"e_1_3_2_37_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Ravi Sachin","year":"2016","unstructured":"Sachin Ravi and Hugo Larochelle. 2016. Optimization as a model for few-shot learning. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_38_2","first-page":"10246","article-title":"On the estimation bias in double q-learning","volume":"34","author":"Ren Zhizhou","year":"2021","unstructured":"Zhizhou Ren, Guangxiang Zhu, Hao Hu, Beining Han, Jianglun Chen, and Chongjie Zhang. 2021. On the estimation bias in double q-learning. Advances in Neural Information Processing Systems 34 (2021), 10246\u201310259.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_39_2","first-page":"5916","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Song Zhao","year":"2019","unstructured":"Zhao Song, Ron Parr, and Lawrence Carin. 2019. Revisiting the softmax bellman operator: New benefits and new perspective. In Proceedings of the International Conference on Machine Learning. PMLR, 5916\u20135925."},{"key":"e_1_3_2_40_2","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton Richard S.","year":"2018","unstructured":"Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction (2nd ed.). MIT Press, Cambridge, MA.","edition":"2"},{"key":"e_1_3_2_41_2","first-page":"255","volume-title":"Proceedings of the 4th Connectionist Models Summer School","author":"Thrun Sebastian","year":"1993","unstructured":"Sebastian Thrun and Anton Schwartz. 1993. Issues in using function approximation for reinforcement learning. In Proceedings of the 4th Connectionist Models Summer School, 255\u2013263."},{"key":"e_1_3_2_43_2","unstructured":"Hado Van Hasselt. 2013. Estimating the maximum expected value: An analysis of (nested) cross validation and the maximum sample average. arXiv:1302.7175. Retrieved from https:\/\/arxiv.org\/pdf\/1302.7175"},{"key":"e_1_3_2_44_2","first-page":"24778","article-title":"Adaptive ensemble Q-learning: Minimizing estimation bias via error feedback","volume":"34","author":"Wang Hang","year":"2021","unstructured":"Hang Wang, Sen Lin, and Junshan Zhang. 2021. Adaptive ensemble Q-learning: Minimizing estimation bias via error feedback. Advances in Neural Information Processing Systems 34 (2021), 24778\u201324790.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_45_2","volume-title":"Learning from Delayed Rewards","author":"Watkins Christopher John Cornish Hellaby","year":"1989","unstructured":"Christopher John Cornish Hellaby Watkins. 1989. Learning from Delayed Rewards. Cambridge University."},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.039"},{"key":"e_1_3_2_47_2","first-page":"8674512","article-title":"Multiagent reinforcement learning-based taxi predispatching model to balance taxi supply and demand","volume":"2020","author":"Yang Yongjian","year":"2020","unstructured":"Yongjian Yang, Xintao Wang, Yuanbo Xu, and Qiuyang Huang. 2020. Multiagent reinforcement learning-based taxi predispatching model to balance taxi supply and demand. Journal of Advanced Transportation 2020 (2020), 8674512.","journal-title":"Journal of Advanced Transportation"},{"key":"e_1_3_2_48_2","doi-asserted-by":"crossref","first-page":"120255","DOI":"10.1016\/j.ins.2024.120255","article-title":"Explorer-actor-critic: Better actors for deep reinforcement learning","volume":"662","author":"Zhang Junwei","year":"2024","unstructured":"Junwei Zhang, Shuai Han, Xi Xiong, Sheng Zhu, and Shuai L\u00fc. 2024. Explorer-actor-critic: Better actors for deep reinforcement learning. Information Sciences 662 (2024), Article 120255.","journal-title":"Information Sciences"},{"key":"e_1_3_2_49_2","first-page":"15313","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"37","author":"Zhang Linrui","year":"2023","unstructured":"Linrui Zhang, Qin Zhang, Li Shen, Bo Yuan, Xueqian Wang, and Dacheng Tao. 2023. Evaluating model-free reinforcement learning toward safety-critical tasks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, 15313\u201315321."},{"key":"e_1_3_2_50_2","first-page":"3455","volume-title":"Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI)","author":"Zhang Zongzhang","year":"2017","unstructured":"Zongzhang Zhang, Zhiyuan Pan, and Mykel J. Kochenderfer. 2017. Weighted double Q-learning. In Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI), 3455\u20133461."},{"key":"e_1_3_2_51_2","first-page":"11185","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"35","author":"Zhu Rong","year":"2021","unstructured":"Rong Zhu and Mattia Rigotti. 2021. Self-correcting Q-learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 11185\u201311192."}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3688849","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3688849","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:10Z","timestamp":1750291450000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3688849"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,12]]},"references-count":48,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2024,11,30]]}},"alternative-id":["10.1145\/3688849"],"URL":"https:\/\/doi.org\/10.1145\/3688849","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,12]]},"assertion":[{"value":"2023-05-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}