{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:17:46Z","timestamp":1750220266044,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":10,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,2,26]],"date-time":"2022-02-26T00:00:00Z","timestamp":1645833600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,2,26]]},"DOI":"10.1145\/3524383.3524432","type":"proceedings-article","created":{"date-parts":[[2022,7,26]],"date-time":"2022-07-26T23:26:41Z","timestamp":1658878001000},"page":"98-102","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Historical knowledge self-testing and training based on control decision"],"prefix":"10.1145","author":[{"given":"Rong","family":"Zhang","sequence":"first","affiliation":[{"name":"Junior High School,Shenzhen Middle School, China"}]},{"given":"Jianqi","family":"Zhong","sequence":"additional","affiliation":[{"name":"Shenzhen University, China"}]}],"member":"320","published-online":{"date-parts":[[2022,7,26]]},"reference":[{"volume-title":"Deep Reinforcement Learning that Matters. arXiv: 1709.06560","year":"2017","key":"e_1_3_2_1_1_1","unstructured":"Henderson, Peter , Deep Reinforcement Learning that Matters. arXiv: 1709.06560 ( 2017 ). Henderson, Peter, Deep Reinforcement Learning that Matters. arXiv: 1709.06560 (2017)."},{"key":"e_1_3_2_1_2_1","unstructured":"imothy P. Lillicrap Continuous Control with Deep Reinforcement Learning. arXiv: 1509:02971. [C].ICLR 2016  imothy P. Lillicrap Continuous Control with Deep Reinforcement Learning. arXiv: 1509:02971. [C].ICLR 2016"},{"key":"e_1_3_2_1_3_1","unstructured":"P Dayan G E Hinton. Feudal Reinforcement Learning. Advances in Neural Information Processing Systems 5 [NIPS Conference]November 1992 Pages 271\u2013278.  P Dayan G E Hinton. Feudal Reinforcement Learning. Advances in Neural Information Processing Systems 5 [NIPS Conference]November 1992 Pages 271\u2013278."},{"key":"e_1_3_2_1_4_1","unstructured":"Hado van Hasselt Deep Reinforcement Learning with Double Q-learning. arXiv:1509:06461.  Hado van Hasselt Deep Reinforcement Learning with Double Q-learning. arXiv:1509:06461."},{"key":"e_1_3_2_1_5_1","first-page":"293","volume":"8","author":"Reactive Agents Based On Self-Improving","year":"1992","unstructured":"Long-ji Lin. Self-Improving Reactive Agents Based On Reinforcement Learning , Planning and Teaching. Machine Learning , 8 , 293 - 321 ( 1992 ). Long-ji Lin. Self-Improving Reactive Agents Based On Reinforcement Learning, Planning and Teaching. Machine Learning, 8, 293-321 (1992).","journal-title":"Teaching. Machine Learning"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/1577069.1755839"},{"key":"e_1_3_2_1_7_1","first-page":"1","volume-title":"Computer Science","volume":"45","author":"Xingyu Zhao","year":"2018","unstructured":"Zhao Xingyu , Ding Shifei . A review of deep reinforcement learning research [J] . Computer Science , July 2018 , Volume 45 , Issue 7 , 1 - 6 . Zhao Xingyu, Ding Shifei. A review of deep reinforcement learning research [J]. Computer Science, July 2018, Volume 45, Issue 7, 1-6."},{"key":"e_1_3_2_1_8_1","first-page":"39","volume-title":"Chinese Journal of Electronics","author":"Hao Wang","year":"2008","unstructured":"Wang Hao , Gao Yang , Chen Xingguo . Transfer in reinforcement learning: methods and progress[J] . Chinese Journal of Electronics , December 2008 , Issue 12A , 39 - 43 . Wang Hao, Gao Yang, Chen Xingguo. Transfer in reinforcement learning: methods and progress[J]. Chinese Journal of Electronics, December 2008, Issue 12A, 39-43."},{"key":"e_1_3_2_1_9_1","volume-title":"Journal of the Internet of Things","volume":"3","author":"Ruijin Ding","year":"2019","unstructured":"Ding Ruijin , Gao Feifei , Xing Ling . Intelligent routing strategy of the Internet of Things based on deep reinforcement learning [J] . Journal of the Internet of Things , June 2019 , Vol. 3 No. 2, 56-63. Ding Ruijin, Gao Feifei, Xing Ling. Intelligent routing strategy of the Internet of Things based on deep reinforcement learning [J]. Journal of the Internet of Things, June 2019, Vol. 3 No. 2, 56-63."},{"key":"e_1_3_2_1_10_1","first-page":"1","volume-title":"Chinese Journal of Computers","volume":"40","author":"Quan Liu","year":"2017","unstructured":"Liu Quan , Zhai Jianwei , Zhang Zongchang , Zhong Shan , Zhou Qian , Zhang Peng , Xu Jin . A review of deep reinforcement learning [J] . Chinese Journal of Computers , 2017 Paper Online Publication No. 1 , Volume 40 , 1 - 28 . Liu Quan, Zhai Jianwei, Zhang Zongchang, Zhong Shan, Zhou Qian, Zhang Peng, Xu Jin. A review of deep reinforcement learning [J]. Chinese Journal of Computers, 2017 Paper Online Publication No. 1, Volume 40, 1- 28."}],"event":{"name":"ICBDE'22: The 2022 5th International Conference on Big Data and Education","acronym":"ICBDE'22","location":"Shanghai China"},"container-title":["Proceedings of the 5th International Conference on Big Data and Education"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3524383.3524432","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3524383.3524432","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:58Z","timestamp":1750188658000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3524383.3524432"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,26]]},"references-count":10,"alternative-id":["10.1145\/3524383.3524432","10.1145\/3524383"],"URL":"https:\/\/doi.org\/10.1145\/3524383.3524432","relation":{},"subject":[],"published":{"date-parts":[[2022,2,26]]},"assertion":[{"value":"2022-07-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}