{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T12:59:40Z","timestamp":1769777980188,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557189","type":"print"},{"value":"9789819557196","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5719-6_9","type":"book-chapter","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T20:34:44Z","timestamp":1769718884000},"page":"130-145","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Hierarchical Reinforcement Learning Method Based on\u00a0Decision Frequency and\u00a0Internal Reward Mechanism"],"prefix":"10.1007","author":[{"given":"Cong","family":"Wang","sequence":"first","affiliation":[]},{"given":"Mingqiang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yuewei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xiaopan","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xiaohui","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Binhao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jianxin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yunliang","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"issue":"13","key":"9_CR1","doi-asserted-by":"publisher","first-page":"7170","DOI":"10.1007\/s10489-024-05436-8","volume":"54","author":"J Lee","year":"2024","unstructured":"Lee, J., Seo, Y.: Q-learning based on strategic artificial potential field for path planning enabling concealment and cover in ground battlefield environments. Appl. Intell. 54(13), 7170\u20137200 (2024)","journal-title":"Appl. Intell."},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Boron, J., Darken, C.: Developing combat behavior through reinforcement learning in wargames and simulations. In: 2020 IEEE Conference on Games (CoG), pp. 728\u2013731 (2020)","DOI":"10.1109\/CoG47356.2020.9231609"},{"issue":"7","key":"9_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/electronics14071445","volume":"14","author":"J Lee","year":"2025","unstructured":"Lee, J., Kim, N.: Development of machine learning-based indicators for predicting comeback victories using the bounty mechanism in moba games. Electronics 14(7), 1\u201325 (2025)","journal-title":"Electronics"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"BarroseS\u00e1, G.C., Madeira, C.A.G.A.: Deep reinforcement learning in real-time strategy games: a systematic literature review: deep reinforcement learning in real-time strategy games. Appl. Intell. 55(4), 1\u201316 (2025)","DOI":"10.1007\/s10489-024-06220-4"},{"key":"9_CR5","doi-asserted-by":"crossref","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) (2023)","DOI":"10.1007\/s10462-023-10620-2"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Cho, H., Yoo, S., Jung, B.C., Kang, J.: Enhancing battlefield awareness: an aerial ris-assisted isac system with deep reinforcement learning. In: MILCOM 2024 - 2024 IEEE Military Communications Conference (MILCOM), pp. 469\u2013474 (2024)","DOI":"10.1109\/MILCOM61039.2024.10774028"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Zhao, X.Y., Yang, M., Peng, C., Wang, C.: Research on intelligent operational assisted decision-making of naval battlefield based on deep reinforcement learning. In: Proceedings of the 3rd International Conference on Advanced Information Science and System (2022)","DOI":"10.1145\/3503047.3503057"},{"key":"9_CR8","unstructured":"Palma, G., Santos, P.A., Dias, J.: Playing hex and counter wargames using reinforcement learning and recurrent neural networks (2025)"},{"issue":"6","key":"9_CR9","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1007\/s10462-025-11166-1","volume":"58","author":"Y Wang","year":"2025","unstructured":"Wang, Y., Wang, Y., Tian, F., Ma, J., Jin, Q.: Intelligent games meeting with multi-agent deep reinforcement learning: a comprehensive review. Artif. Intell. Rev. 58(6), 165 (2025)","journal-title":"Artif. Intell. Rev."},{"issue":"4","key":"9_CR10","first-page":"786","volume":"35","author":"D Shi","year":"2023","unstructured":"Shi, D., Yan, X., Gong, L., Zhang, J., Guan, D., Wei, M.: Multi-agent cooperative combat simulation in naval battlefield with reinforcement learning. J. Syst. Simul. 35(4), 786\u2013796 (2023)","journal-title":"J. Syst. Simul."},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Wang, H., Tang, H., Hao, J., Hao, X., Fu, Y., Ma, Y.: Large scale deep reinforcement learning in war-games. In: 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 1693\u20131699 (2020)","DOI":"10.1109\/BIBM49941.2020.9313387"},{"key":"9_CR12","doi-asserted-by":"publisher","first-page":"2991","DOI":"10.1007\/s00530-022-00922-w","volume":"29","author":"W Chen","year":"2022","unstructured":"Chen, W., Nie, J.: A maddpg-based multi-agent antagonistic algorithm for sea battlefield confrontation. Multimedia Syst. 29, 2991\u20133000 (2022)","journal-title":"Multimedia Syst."},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Kim, G.S., Lee, S., Woo, T., Park, S.: Cooperative reinforcement learning for military drones over large-scale battlefields. IEEE Trans. Intell. Veh. 1\u201311 (2024)","DOI":"10.1109\/TIV.2024.3472213"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Niel, R., Krebbers, J., Drugan, M.M., Wiering, M.A.: Hierarchical reinforcement learning for real-time strategy games. In: 10th International Conference on Agents and Artificial Intelligence, pp. 470\u2013477 (2018)","DOI":"10.5220\/0006593804700477"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Hierarchical reinforcement learning for multi-agent moba game (2019)","DOI":"10.1504\/IJWMC.2019.100069"},{"key":"9_CR16","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms, pp. 1\u201312. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"9_CR17","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, vol.\u00a080, pp. 1861\u20131870 (2018)"},{"key":"9_CR18","unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: Proceedings of the 35th International Conference on Machine Learning, vol.\u00a080, pp. 1587\u20131596 (2018)"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Mnih, V., et\u00a0al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Van\u00a0Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a030 (2016)","DOI":"10.1609\/aaai.v30i1.10295"}],"container-title":["Lecture Notes in Computer Science","Web and Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5719-6_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T20:34:49Z","timestamp":1769718889000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5719-6_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557189","9789819557196"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5719-6_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"30 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APWeb-WAIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenyang","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"apwebwaim2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/apweb2025.sau.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}