{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T04:48:14Z","timestamp":1746679694615,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819947607"},{"type":"electronic","value":"9789819947614"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-981-99-4761-4_55","type":"book-chapter","created":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T16:02:10Z","timestamp":1690732930000},"page":"653-666","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Advancing Air Combat Tactics with Improved Neural Fictitious Self-play Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Shaoqin","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baofeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinchen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,31]]},"reference":[{"key":"55_CR1","unstructured":"Bansal, T., Pachocki, J., Sidor, S., Sutskever, I., Mordatch, I.: Emergent complexity via multi-agent competition. arXiv preprint arXiv:1710.03748 (2017)"},{"key":"55_CR2","unstructured":"Burgin, G.H.: Improvements to the adaptive maneuvering logic program. Technical report (1986)"},{"issue":"1","key":"55_CR3","first-page":"2167","volume":"6","author":"N Ernest","year":"2016","unstructured":"Ernest, N., Carroll, D., Schumacher, C., et al.: Genetic fuzzy based artificial intelligence for unmanned combat aerial vehicle control in simulated air combat missions. J. Def. Manag. 6(1), 2167\u20132374 (2016)","journal-title":"J. Def. Manag."},{"key":"55_CR4","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning, pp. 1587\u20131596. PMLR (2018)"},{"key":"55_CR5","doi-asserted-by":"crossref","unstructured":"Guo, J., et al.: Maneuver decision of UAV in air combat based on deterministic policy gradient. In: 2022 IEEE 17th International Conference on Control & Automation (ICCA), pp. 243\u2013248. IEEE (2022)","DOI":"10.1109\/ICCA54724.2022.9831941"},{"key":"55_CR6","unstructured":"Haarnoja, T., Tang, H., Abbeel, P., Levine, S.: Reinforcement learning with deep energy-based policies. In: International Conference on Machine Learning, pp. 1352\u20131361. PMLR (2017)"},{"key":"55_CR7","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"},{"key":"55_CR8","unstructured":"Heinrich, J., Lanctot, M., Silver, D.: Fictitious self-play in extensive-form games. In: International Conference on Machine Learning, pp. 805\u2013813. PMLR (2015)"},{"key":"55_CR9","unstructured":"Heinrich, J., Silver, D.: Deep reinforcement learning from self-play in imperfect information games. arXiv preprint arXiv:1603.01121 (2016)"},{"key":"55_CR10","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"55_CR11","doi-asserted-by":"publisher","unstructured":"Liu, P., Ma, Y.: A deep reinforcement learning based intelligent decision method for UCAV air combat. In: Mohamed Ali, M., Wahid, H., Mohd Subha, N., Sahlan, S., Md. Yunus, M., Wahap, A. (eds.) AsiaSim 2017. CCIS, vol. 751, Part I, pp. 274\u2013286. Springer, Singapore (2017). https:\/\/doi.org\/10.1007\/978-981-10-6463-0_24","DOI":"10.1007\/978-981-10-6463-0_24"},{"key":"55_CR12","doi-asserted-by":"crossref","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"key":"55_CR13","doi-asserted-by":"crossref","unstructured":"Piao, H., et al.: Beyond-visual-range air combat tactics auto-generation by reinforcement learning. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9207088"},{"key":"55_CR14","doi-asserted-by":"crossref","unstructured":"Pope, A.P., et al.: Hierarchical reinforcement learning for air-to-air combat. In: 2021 International Conference on Unmanned Aircraft Systems (ICUAS), pp. 275\u2013284. IEEE (2021)","DOI":"10.1109\/ICUAS51884.2021.9476700"},{"key":"55_CR15","doi-asserted-by":"crossref","unstructured":"Qiu, X., Yao, Z., Tan, F., Zhu, Z., Lu, J.G.: One-to-one air-combat maneuver strategy based on improved TD3 algorithm. In: 2020 Chinese Automation Congress (CAC), pp. 5719\u20135725. IEEE (2020)","DOI":"10.1109\/CAC51589.2020.9327310"},{"key":"55_CR16","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"55_CR17","doi-asserted-by":"crossref","unstructured":"Sun, Z., et al.: Multi-agent hierarchical policy gradient for air combat tactics emergence via self-play. Eng. Appl. Artif. Intell. 98, 104112 (2021)","DOI":"10.1016\/j.engappai.2020.104112"},{"key":"55_CR18","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30 (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"55_CR19","doi-asserted-by":"crossref","unstructured":"Yang, Q., Zhang, J., Shi, G., et al.: Maneuver decision of UAV in short-range air combat based on deep reinforcement learning. IEEE Access 8, 363\u2013378 (2019)","DOI":"10.1109\/ACCESS.2019.2961426"},{"key":"55_CR20","doi-asserted-by":"crossref","unstructured":"Zheng, H., Deng, Y., Hu, Y.: Fuzzy evidential influence diagram and its evaluationalgorithm. Knowl. Based Syst. 131, 28\u201345 (2017)","DOI":"10.1016\/j.knosys.2017.05.024"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-4761-4_55","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T23:23:10Z","timestamp":1690932190000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-4761-4_55"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819947607","9789819947614"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-4761-4_55","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"31 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2023a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2023\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}