{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:11:04Z","timestamp":1784099464331,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819227587","type":"print"},{"value":"9789819227594","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"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\/978-981-92-2759-4_38","type":"book-chapter","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T06:52:33Z","timestamp":1784098353000},"page":"519-531","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DP-QMIX: Enhanced QMIX with\u00a0Adaptive Death Prediction Model for\u00a0Multi-agent Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5545-3117","authenticated-orcid":false,"given":"Qi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,16]]},"reference":[{"issue":"4","key":"38_CR1","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1287\/moor.27.4.819.297","volume":"27","author":"DS Bernstein","year":"2002","unstructured":"Bernstein, D.S., Givan, R., Immerman, N., Zilberstein, S.: The complexity of decentralized control of Markov decision processes. Math. Oper. Res. 27(4), 819\u2013840 (2002)","journal-title":"Math. Oper. Res."},{"key":"38_CR2","doi-asserted-by":"crossref","unstructured":"Chai, J., Li, W., Zhu, Y.e.a.: Unmas: Multiagent reinforcement learning for unshaped cooperative scenarios. IEEE Trans. Neural Netw. Learn. Syst. 34(4), 2093\u20132104 (2021)","DOI":"10.1109\/TNNLS.2021.3105869"},{"key":"38_CR3","doi-asserted-by":"publisher","first-page":"37567","DOI":"10.52202\/075280-1634","volume":"36","author":"B Ellis","year":"2023","unstructured":"Ellis, B., et al.: Smacv2: an improved benchmark for cooperative multi-agent reinforcement learning. Adv. Neural. Inf. Process. Syst. 36, 37567\u201337593 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"38_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.107093","volume":"184","author":"S Fu","year":"2025","unstructured":"Fu, S., Zhao, S., Li, T., Yan, Y.: Qtypemix: enhancing multi-agent cooperative strategies through heterogeneous and homogeneous value decomposition. Neural Netw. 184, 107093 (2025)","journal-title":"Neural Netw."},{"key":"38_CR5","unstructured":"Ha, D., Dai, A.M., Le, Q.V.: Hypernetworks. In: Proceedings of the International Conference on Learning Representations (2017)"},{"issue":"8","key":"38_CR6","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"38_CR7","unstructured":"Hu, J., Wang, S., Jiang, S., Wang, M.: Rethinking the implementation tricks and monotonicity constraint in cooperative multi-agent reinforcement learning. In: Proceedings of the Second Blogpost Track at ICLR 2023 (2023)"},{"key":"38_CR8","doi-asserted-by":"crossref","unstructured":"Jo, Y., Lee, S., Yeom, J.E.A.: Fox: formation-aware exploration in multi-agent reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 12985\u201312994 (2024)","DOI":"10.1609\/aaai.v38i12.29196"},{"key":"38_CR9","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.neucom.2016.01.031","volume":"190","author":"L Kraemer","year":"2016","unstructured":"Kraemer, L., Banerjee, B.: Multi-agent reinforcement learning as a rehearsal for decentralized planning. Neurocomputing 190, 82\u201394 (2016)","journal-title":"Neurocomputing"},{"key":"38_CR10","doi-asserted-by":"crossref","unstructured":"Liu, Y., Luo, G., Yuan, Q.E.A.: GPLight: grouped multi-agent reinforcement learning for large-scale traffic signal control. In: Proceedings of the IJCAI, pp. 199\u2013207 (2023)","DOI":"10.24963\/ijcai.2023\/23"},{"key":"38_CR11","series-title":"IFIP Advances in Information and Communication Technology","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1007\/978-3-030-85914-5_62","volume-title":"Advances in Production Management Systems. Artificial Intelligence for Sustainable and Resilient Production Systems","author":"O Lohse","year":"2021","unstructured":"Lohse, O., P\u00fctz, N., H\u00f6rmann, K.: Implementing an online scheduling approach for production with multi agent proximal policy optimization (MAPPO). In: Dolgui, A., Bernard, A., Lemoine, D., von Cieminski, G., Romero, D. (eds.) APMS 2021. IAICT, vol. 634, pp. 586\u2013595. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-85914-5_62"},{"key":"38_CR12","doi-asserted-by":"crossref","unstructured":"Oliehoek, F.A., et al.: A concise introduction to decentralized POMDPs, vol. 1. Springer (2016)","DOI":"10.1007\/978-3-319-28929-8_1"},{"key":"38_CR13","unstructured":"Papoudakis, G., Christianos, F., Sch\u00e4fer, L., Albrecht, S.V.: Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks. In: Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS) (2021)"},{"key":"38_CR14","unstructured":"Rashid, T., Samvelyan, M., De\u00a0Witt, C.S.E.A.: Monotonic value function factorisation for deep multi-agent reinforcement learning. J. Mach. Learn. Res. 21(178), 1\u201351 (2020)"},{"key":"38_CR15","doi-asserted-by":"crossref","unstructured":"Shi, H., Liu, G., Zhang, K.E.A.: Marl sim2real transfer: merging physical reality with digital virtuality in metaverse. IEEE Trans. Syst. Man Cybern. Syst. 53(4), 2107\u20132117 (2022)","DOI":"10.1109\/TSMC.2022.3229213"},{"key":"38_CR16","unstructured":"Son, K., Kim, D., Kang, W.J.E.A.: Qtran: learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: Proceedings of the International conference on machine learning, pp. 5887\u20135896. PMLR (2019)"},{"key":"38_CR17","doi-asserted-by":"crossref","unstructured":"Sunehag, P., Lever, G., Gruslys, A.E.A.: Value-decomposition networks for cooperative multi-agent learning based on team reward. In: Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems, pp. 2085\u20132087. AAMAS \u201918 (2018)","DOI":"10.65109\/JSRC7365"},{"key":"38_CR18","doi-asserted-by":"crossref","unstructured":"Wang, L., Wang, K., Pan, C.E.A.: Multi-agent deep reinforcement learning-based trajectory planning for multi-UAV assisted mobile edge computing. IEEE Trans. Cogn. Commun. Networking 7(1), 73\u201384 (2020)","DOI":"10.1109\/TCCN.2020.3027695"},{"key":"38_CR19","unstructured":"Wang, W., Yang, T., Liu, Y.E.A.: Action semantics network: considering the effects of actions in multiagent systems. In: Proceedings of the International Conference on Learning Representations (2020)"},{"key":"38_CR20","doi-asserted-by":"crossref","unstructured":"Wang, Z., Du, J., Jiang, C.E.A.: Task scheduling for distributed AUV network target hunting and searching: An energy-efficient AOI-aware DMAPPO approach. IEEE Internet Things J. 10(9), 8271\u20138285 (2022)","DOI":"10.1109\/JIOT.2022.3230916"},{"key":"38_CR21","doi-asserted-by":"crossref","unstructured":"Wen, G., Fu, J., Dai, P., Zhou, J.: DTDE: a new cooperative multi-agent reinforcement learning framework. Innovation 2(4) (2021)","DOI":"10.1016\/j.xinn.2021.100162"},{"key":"38_CR22","unstructured":"Zhang, R., et al.: Multi-agent reinforcement learning for autonomous driving: a survey. CoRR abs\/2408.09675 (2024)"}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-2759-4_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T06:52:42Z","timestamp":1784098362000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-2759-4_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"ISBN":["9789819227587","9789819227594"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-2759-4_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,16]]},"assertion":[{"value":"16 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Science, Engineering and Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","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":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 July 2026","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":"ksem2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ksem2026.rosc.org.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}