{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T12:40:09Z","timestamp":1695213609956},"reference-count":7,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,12,3]],"date-time":"2021-12-03T00:00:00Z","timestamp":1638489600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,12,3]],"date-time":"2021-12-03T00:00:00Z","timestamp":1638489600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Front. Comput. Sci."],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1007\/s11704-021-0250-y","type":"journal-article","created":{"date-parts":[[2021,12,3]],"date-time":"2021-12-03T02:02:27Z","timestamp":1638496947000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Improving deep reinforcement learning by safety guarding model via hazardous experience planning"],"prefix":"10.1007","volume":"16","author":[{"given":"Pai","family":"Peng","sequence":"first","affiliation":[]},{"given":"Fei","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Xinghong","family":"Ling","sequence":"additional","affiliation":[]},{"given":"Peiyao","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Quan","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,12,3]]},"reference":[{"issue":"6","key":"250_CR1","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","volume":"34","author":"A Kai","year":"2017","unstructured":"Kai A, Deisenroth M P, Brundage M, Bharath A A. Deep reinforcement learning: a brief survey. IEEE Signal Processing Magazine, 2017, 34(6): 26\u201338","journal-title":"IEEE Signal Processing Magazine"},{"key":"250_CR2","doi-asserted-by":"crossref","unstructured":"Cheng R, Orosz G, Murray R M, Burdick J W. End-to-end safe reinforcement learning through barrier functions for safety-critical continuous control tasks. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2019, 3387\u20133395","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"250_CR3","unstructured":"Saunders W, Sastry G, Stuhlmueller A, Evans O. Trial without error: towards safe reinforcement learning via human intervention. In: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems. 2018, 2067\u20132069"},{"key":"250_CR4","unstructured":"Achiam J, Held D, Tamar A, Abbeel P. Constrained policy optimization. In: Proceedings of the International Conference on Machine Learning. 2017, 22\u201331"},{"key":"250_CR5","first-page":"1437","volume":"16","author":"J Garc\u00eda","year":"2015","unstructured":"Garc\u00eda J, Fern\u00e1ndez F. A comprehensive survey on safe reinforcement learning. Journal of Machine Learning Research, 2015, 16: 1437\u20131480","journal-title":"Journal of Machine Learning Research"},{"key":"250_CR6","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1016\/j.robot.2017.11.010","volume":"100","author":"K Chatzilygeroudis","year":"2018","unstructured":"Chatzilygeroudis K, Vassiliades V, Mouret J B. Reset-free trial-and-error learning for robot damage recovery. Robotics and Autonomous Systems, 2018, 100: 236\u2013250","journal-title":"Robotics and Autonomous Systems"},{"issue":"8","key":"250_CR7","first-page":"1812","volume":"42","author":"F Zhu","year":"2019","unstructured":"Zhu F, Wu W, Fu Y, Liu Q. A dual deep network based secure deep reinforcement learning method. Chinese Journal of Computers, 2019, 42(8): 1812\u20131826","journal-title":"Chinese Journal of Computers"}],"container-title":["Frontiers of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-021-0250-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11704-021-0250-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-021-0250-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T21:04:28Z","timestamp":1695157468000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11704-021-0250-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,3]]},"references-count":7,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,8]]}},"alternative-id":["250"],"URL":"https:\/\/doi.org\/10.1007\/s11704-021-0250-y","relation":{},"ISSN":["2095-2228","2095-2236"],"issn-type":[{"value":"2095-2228","type":"print"},{"value":"2095-2236","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,3]]},"assertion":[{"value":"5 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 December 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"164320"}}