{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:26:27Z","timestamp":1742912787818,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":15,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819771806"},{"type":"electronic","value":"9789819771813"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-7181-3_31","type":"book-chapter","created":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T08:37:21Z","timestamp":1724315841000},"page":"391-400","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Distributed Advantage-Based Weights Reshaping Algorithm with Sparse Reward"],"prefix":"10.1007","author":[{"given":"Yupeng","family":"Fu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyang","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziqiang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Limin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,21]]},"reference":[{"issue":"1","key":"31_CR1","first-page":"1","volume":"22","author":"Z Wangh","year":"2020","unstructured":"Wangh, Z., Li, H., Wu, H.L., et al.: Improving maneuver strategy in air combat by alternate freeze games with a deep reinforcement learning algorithm. Math. Probl. Eng. 22(1), 1\u201317 (2020)","journal-title":"Math. Probl. Eng."},{"issue":"2","key":"31_CR2","first-page":"443","volume":"43","author":"W Ma","year":"2021","unstructured":"Ma, W., Li, H., Wang, Z., et al.: Close air combat maneuver decision based on deep stochastic game. Syst. Eng. Electron. 43(2), 443\u2013451 (2021)","journal-title":"Syst. Eng. Electron."},{"issue":"1","key":"31_CR3","first-page":"36","volume":"2","author":"XG Li","year":"2020","unstructured":"Li, X.G., Li, Q.: Technical analysis of typical intelligent game system and development prospect of intelligent command and control system. Chin. J. Intell. Sci. Technol. 2(1), 36\u201342 (2020)","journal-title":"Chin. J. Intell. Sci. Technol."},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Pope, A.P., Ide, J.S., Micovic, D., et al.: Hierarchical Reinforcement Learning for Air-to-Air Combat[DB\/OL]. arXiv: 2105.00990 (2021)","DOI":"10.1109\/ICUAS51884.2021.9476700"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Sufiyan, D., Win, L., Win, S., et al.: A reinforcement learning approach for control of a nature-inspired aerial vehicle. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 6030\u20136036. IEEE, Piscataway (2019)","DOI":"10.1109\/ICRA.2019.8794446"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Zhen, Y., Hao, M., Sun, W.: Deep reinforcement learning attitude control of fixed-wing UAVs. In: 2020 3rd International Conference on Unmanned Systems (ICUS), pp. 239\u2013244. IEEE, Piscataway (2020)","DOI":"10.1109\/ICUS50048.2020.9274875"},{"key":"31_CR7","unstructured":"Wang, C., Yan, C., Xiang, X., et al.: A continuous actor-critic reinforcement learning approach to flocking with fixed-wing UAVs. In: Asian Conference on Machine Learning, pp. 239\u2013244. Berlin: Springer (2020)"},{"issue":"4","key":"31_CR8","first-page":"126731","volume":"44","author":"P Zhou","year":"2023","unstructured":"Zhou, P., Huang, J., Zhang, S., Liu, G., Shu, B., Tang, J.: Intelligent air combat decision making and simulation based on deep reinforcement learning. ACTA Aeronauticaet Astronaut. Sin. 44(4), 126731 (2023)","journal-title":"ACTA Aeronauticaet Astronaut. Sin."},{"key":"31_CR9","unstructured":"Wu, Y.J., Lai, J., Chen, X.L., et al.: Research on the application of reinforcement learning algorithm in dicision support of beyond-visual-range air combat. Aero Weaponry 28(2), 55\u201361 (2021)"},{"issue":"12","key":"31_CR10","doi-asserted-by":"publisher","first-page":"2225","DOI":"10.1360\/SSI-2022-0185","volume":"52","author":"H Wang","year":"2022","unstructured":"Wang, H., Zhou, X., Deng, Y.M., et al.: A hierarchical decision making method for multi-aircraft air combat confrontation. Sci. Sin. Inform. 52(12), 2225\u20132238 (2022)","journal-title":"Sci. Sin. Inform."},{"key":"31_CR11","unstructured":"Oh, J., Guo, Y., Singh, S., et al.: Self-imitation learning. In: Proceedings of the 35th International Conference on Machine Learning, pp. 3778\u20133887. ACM, New York (2018)"},{"key":"31_CR12","unstructured":"Fu, Y.P., Deng, X.Y., Zhu, Z.Q., et al.: Value-filter based air-combat maneuvering optimization. Acta Aeronautica et Astronaut. Sin. 44(23), 628871 (2023)"},{"key":"31_CR13","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., et al.: Proximal policy optimization algorithms [DB\/OL]. arXiv:1707.06347 (2017)"},{"key":"31_CR14","unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: ICML (2018)"},{"key":"31_CR15","unstructured":"Haarnoja, T., Zhou, A., Hartikainen, K., et al.: Soft Actor-Critic Algorithms and Applications[DB\/OL]. arXiv: 1801.01290"}],"container-title":["Lecture Notes in Computer Science","Advances in Swarm Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-7181-3_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T09:10:03Z","timestamp":1724317803000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-7181-3_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819771806","9789819771813"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-7181-3_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"21 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICSI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Swarm Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xining","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"swarm2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iasei.org\/icsi2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}