{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T07:04:45Z","timestamp":1784012685611,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234431","type":"print"},{"value":"9789819234448","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3444-8_47","type":"book-chapter","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T06:17:55Z","timestamp":1784009875000},"page":"571-582","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Contrastive Reinforcement Learning Approach for Beyond-Visual-Range Air Combat Decision-Making"],"prefix":"10.1007","author":[{"given":"Lianmeng","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minchi","family":"Kuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingxiang","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"issue":"3","key":"47_CR1","doi-asserted-by":"publisher","DOI":"10.3390\/aerospace12030265","volume":"12","author":"C Chen","year":"2025","unstructured":"Chen, C., Song, T., Mo, L., Lv, M., Lin, D.: Autonomous dogfight decision-making for air combat based on reinforcement learning with automatic opponent sampling. Aerospace. 12(3), 265 (2025). https:\/\/doi.org\/10.3390\/aerospace12030265","journal-title":"Aerospace"},{"key":"47_CR2","first-page":"1597","volume-title":"Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research","author":"T Chen","year":"2020","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 119, pp. 1597\u20131607 (2020)"},{"key":"47_CR3","first-page":"1861","volume-title":"Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research","author":"T Haarnoja","year":"2018","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 80, pp. 1861\u20131870 (2018)"},{"key":"47_CR4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00974","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"K He","year":"2020","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00974"},{"key":"47_CR5","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-00463-y","volume":"15","author":"L Huo","year":"2025","unstructured":"Huo, L., Wang, C., Han, Y.: Autonomous air combat decision making via graph neural networks and reinforcement learning. Sci. Rep. 15, 16169 (2025). https:\/\/doi.org\/10.1038\/s41598-025-00463-y","journal-title":"Sci. Rep."},{"key":"47_CR6","first-page":"5639","volume-title":"Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research","author":"M Laskin","year":"2020","unstructured":"Laskin, M., Srinivas, A., Abbeel, P.: CURL: contrastive unsupervised representations for reinforcement learning. In: Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 119, pp. 5639\u20135650 (2020)"},{"issue":"12","key":"47_CR7","doi-asserted-by":"publisher","DOI":"10.3390\/e26121036","volume":"26","author":"W Li","year":"2024","unstructured":"Li, W., Fang, F., Peng, D., Han, S.: An intelligent maneuver decision-making approach for air combat based on deep reinforcement learning and transformer networks. Entropy. 26(12), 1036 (2024). https:\/\/doi.org\/10.3390\/e26121036","journal-title":"Entropy"},{"key":"47_CR8","doi-asserted-by":"publisher","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971. (2016). https:\/\/doi.org\/10.48550\/arXiv.1509.02971","DOI":"10.48550\/arXiv.1509.02971"},{"key":"47_CR9","volume-title":"International Conference on Learning Representations (ICLR)","author":"YJ Ma","year":"2024","unstructured":"Ma, Y.J., et al.: Eureka: human-level reward design via coding large language models. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"47_CR10","first-page":"1928","volume-title":"Proceedings of the 33rd International Conference on Machine Learning. Proceedings of Machine Learning Research","author":"V Mnih","year":"2016","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: Proceedings of the 33rd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 48, pp. 1928\u20131937 (2016)"},{"issue":"7540","key":"47_CR11","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature. 518(7540), 529\u2013533 (2015). https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"key":"47_CR12","doi-asserted-by":"publisher","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748. (2018). https:\/\/doi.org\/10.48550\/arXiv.1807.03748","DOI":"10.48550\/arXiv.1807.03748"},{"issue":"6","key":"47_CR13","doi-asserted-by":"publisher","first-page":"1371","DOI":"10.1109\/TAI.2022.3222143","volume":"4","author":"AP Pope","year":"2023","unstructured":"Pope, A.P., et al.: Hierarchical reinforcement learning for air combat at DARPA\u2019s alphadogfight trials. IEEE Trans. Artif. Intell. 4(6), 1371\u20131385 (2023). https:\/\/doi.org\/10.1109\/TAI.2022.3222143","journal-title":"IEEE Trans. Artif. Intell."},{"key":"47_CR14","first-page":"1889","volume-title":"Proceedings of the 32nd International Conference on Machine Learning. Proceedings of Machine Learning Research","author":"J Schulman","year":"2015","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: Proceedings of the 32nd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 37, pp. 1889\u20131897 (2015)"},{"key":"47_CR15","doi-asserted-by":"publisher","unstructured":"Schulman, J., Moritz, P., Levine, S., Jordan, M.I., Abbeel, P.: High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438. (2015). https:\/\/doi.org\/10.48550\/arXiv.1506.02438","DOI":"10.48550\/arXiv.1506.02438"},{"key":"47_CR16","doi-asserted-by":"publisher","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347. (2017). https:\/\/doi.org\/10.48550\/arXiv.1707.06347","DOI":"10.48550\/arXiv.1707.06347"},{"key":"47_CR17","doi-asserted-by":"publisher","first-page":"119116","DOI":"10.1109\/ACCESS.2024.3419889","volume":"12","author":"H Wang","year":"2024","unstructured":"Wang, H., Zhou, Z., Jiang, J., Deng, W., Chen, X.: Autonomous air combat maneuver decision-making based on PPO-BWDA. IEEE Access. 12, 119116\u2013119132 (2024). https:\/\/doi.org\/10.1109\/ACCESS.2024.3419889","journal-title":"IEEE Access"},{"issue":"1","key":"47_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10620-2","volume":"57","author":"X Wang","year":"2024","unstructured":"Wang, X., et al.: Deep reinforcement learning-based air combat maneuver decision-making: literature review, implementation tutorial and future direction. Artif. Intell. Rev. 57(1), 1 (2024). https:\/\/doi.org\/10.1007\/s10462-023-10620-2","journal-title":"Artif. Intell. Rev."},{"issue":"16","key":"47_CR19","doi-asserted-by":"publisher","DOI":"10.3390\/app13169421","volume":"13","author":"Y Wei","year":"2023","unstructured":"Wei, Y., Zhang, H., Wang, Y., Huang, C.: Maneuver decision-making through automatic curriculum reinforcement learning without handcrafted reward functions. Appl. Sci. 13(16), 9421 (2023). https:\/\/doi.org\/10.3390\/app13169421","journal-title":"Appl. Sci."},{"key":"47_CR20","volume-title":"International Conference on Learning Representations (ICLR)","author":"T Xie","year":"2024","unstructured":"Xie, T., et al.: Text2reward: reward shaping with language models for reinforcement learning. In: International Conference on Learning Representations (ICLR) (2024)"}],"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\/978-981-92-3444-8_47","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T06:17:57Z","timestamp":1784009877000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3444-8_47"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"ISBN":["9789819234431","9789819234448"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3444-8_47","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]},"assertion":[{"value":"15 July 2026","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":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}