{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T21:02:22Z","timestamp":1784408542297,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":38,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819233809","type":"print"},{"value":"9789819233816","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"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\/978-981-92-3381-6_25","type":"book-chapter","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T20:15:08Z","timestamp":1784405708000},"page":"304-315","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Attention-Based Multi-Agent Reinforcement Learning with Dual Experience Replay Buffers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2776-9925","authenticated-orcid":false,"given":"Yinuo","family":"Yin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4491-9281","authenticated-orcid":false,"given":"Yiyang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"issue":"2","key":"25_CR1","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/TSMCC.2007.913919","volume":"38","author":"L Busoniu","year":"2008","unstructured":"Busoniu, L., Babuska, R., De Schutter, B.: A comprehensive survey of multiagent reinforcement learning. IEEE Trans. Syst. Man Cybern. Part C Appl. Rev. 38(2), 156\u2013172 (2008)","journal-title":"IEEE Trans. Syst. Man Cybern. Part C Appl. Rev."},{"key":"25_CR2","first-page":"1146","volume-title":"International Conference on Machine Learning","author":"J Foerster","year":"2017","unstructured":"Foerster, J., et al.: Stabilising experience replay for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 1146\u20131155. PMLR (2017)"},{"key":"25_CR3","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. Adv. Neural Inf. Proces. Syst. 30 (2017)"},{"key":"25_CR4","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.engappai.2016.11.008","volume":"58","author":"J Hao","year":"2017","unstructured":"Hao, J., Huang, D., Cai, Y., Leung, H.F.: The dynamics of reinforcement social learning in networked cooperative multiagent systems. Eng. Appl. Artif. Intell. 58, 111\u2013122 (2017)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"25_CR5","unstructured":"Andrychowicz, M., et al.: Hindsight experience replay. Adv. Neural Inf. Proces. Syst. 30 (2017)"},{"issue":"6","key":"25_CR6","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1007\/s10458-019-09421-1","volume":"33","author":"P Hernandez-Leal","year":"2019","unstructured":"Hernandez-Leal, P., Kartal, B., Taylor, M.E.: A survey and critique of multiagent deep reinforcement learning. Auton. Agent. Multi-Agent Syst. 33(6), 750\u2013797 (2019)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"issue":"2","key":"25_CR7","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1007\/s10462-021-09996-w","volume":"55","author":"S Gronauer","year":"2022","unstructured":"Gronauer, S., Diepold, K.: Multi-agent deep reinforcement learning: a survey. Artif. Intell. Rev. 55(2), 895\u2013943 (2022)","journal-title":"Artif. Intell. Rev."},{"key":"25_CR8","unstructured":"Konda, V., Tsitsiklis, J.: Actor-critic algorithms. Adv. Neural Inf. Proces. Syst. 12 (1999)"},{"key":"25_CR9","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint https:\/\/arxiv.org\/abs\/1509.02971 (2015)"},{"key":"25_CR10","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Proces. Syst. 30 (2017)"},{"key":"25_CR11","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. arXiv preprint https:\/\/arxiv.org\/abs\/1511.05952 (2015)"},{"issue":"8","key":"25_CR12","doi-asserted-by":"publisher","first-page":"1337","DOI":"10.1109\/LCOMM.2019.2922961","volume":"23","author":"C Qi","year":"2019","unstructured":"Qi, C., Hua, Y., Li, R., Zhao, Z., Zhang, H.: Deep reinforcement learning with discrete normalized advantage functions for resource management in network slicing. IEEE Commun. Lett. 23(8), 1337\u20131341 (2019)","journal-title":"IEEE Commun. Lett."},{"key":"25_CR13","volume-title":"Temporal Credit Assignment in Reinforcement Learning","author":"RS Sutton","year":"1984","unstructured":"Sutton, R.S.: Temporal Credit Assignment in Reinforcement Learning. University of Massachusetts Amherst. PhD dissertation, Amherst, MA, USA (1984)"},{"key":"25_CR14","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"ML Puterman","year":"2014","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. John Wiley & Sons, monograph, Hoboken, NJ, USA (2014)"},{"key":"25_CR15","first-page":"279","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8, 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"25_CR16","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1109\/ICNC.2008.694","volume-title":"2008 Fourth International Conference on Natural Computation","author":"SL Chen","year":"2008","unstructured":"Chen, S.L., Wei, Y.M.: Least-Squares SARSA (Lambda) algorithms for reinforcement learning. In: 2008 Fourth International Conference on Natural Computation, vol. 2, pp. 632\u2013636. IEEE (2008)"},{"issue":"7540","key":"25_CR17","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)","journal-title":"Nature"},{"key":"25_CR18","unstructured":"Sutton, R.S., McAllester, D., Singh, S., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. Adv. Neural Inf. Proces. Syst. 12 (1999)"},{"issue":"178","key":"25_CR19","first-page":"1","volume":"21","author":"T Rashid","year":"2020","unstructured":"Rashid, T., Samvelyan, M., De Witt, C.S., Farquhar, G., Foerster, J., Whiteson, S.: Monotonic value function factorisation for deep multi-agent reinforcement learning. J. Mach. Learn. Res. 21(178), 1\u201351 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"25_CR20","first-page":"5887","volume-title":"International Conference on Machine Learning","author":"K Son","year":"2019","unstructured":"Son, K., Kim, D., Kang, W.J., Hostallero, D.E., Yi, Y.: Qtran: learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 5887\u20135896. PMLR (2019)"},{"key":"25_CR21","unstructured":"Jiang, J., Lu, Z.: Learning attentional communication for multi-agent cooperation. Adv. Neural Inf. Proces. Syst. 31 (2018)"},{"issue":"11","key":"25_CR22","doi-asserted-by":"publisher","first-page":"8235","DOI":"10.1109\/TNNLS.2022.3146858","volume":"34","author":"Z Pu","year":"2022","unstructured":"Pu, Z., Wang, H., Liu, Z., Yi, J., Wu, S.: Attention enhanced reinforcement learning for multi-agent cooperation. IEEE Trans. Neural Networks Learn. Syst. 34(11), 8235\u20138249 (2022)","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"25_CR23","unstructured":"Singh, J., Zheng, L.: Sparse attention guided dynamic value estimation for single-task multi-scene reinforcement learning. arXiv preprint https:\/\/arxiv.org\/abs\/2102.07266 (2021)"},{"key":"25_CR24","first-page":"2961","volume-title":"International Conference on Machine Learning","author":"S Iqbal","year":"2019","unstructured":"Iqbal, S., Sha, F.: Actor-attention-critic for multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 2961\u20132970. PMLR (2019)"},{"key":"25_CR25","volume-title":"Pattern Recognition and Machine Learning","author":"C Bishop","year":"2006","unstructured":"Bishop, C.: Pattern Recognition and Machine Learning, vol. 4. Springer, New York, NY, USA (2006)"},{"key":"25_CR26","unstructured":"Tesauro, G.: Extending q-learning to general adaptive multi-agent systems. Adv. Neural Inf. Proces. Syst. 16 (2003)"},{"key":"25_CR27","unstructured":"Horgan, D., et al.: Distributed prioritized experience replay. arXiv preprint https:\/\/arxiv.org\/abs\/1803.00933 (2018)"},{"key":"25_CR28","unstructured":"Lan, Q., Pan, Y., Luo, J., Mahmood, A.: Memory-efficient reinforcement learning with value-based knowledge consolidation. arXiv preprint https:\/\/arxiv.org\/abs\/2205.10868 (2022)"},{"key":"25_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2025.100886","volume":"60","author":"A Ali","year":"2026","unstructured":"Ali, A., et al.: Advanced computational models for urban traffic flow prediction: a comprehensive review and future directions. Comput Sci Rev. 60, 100886 (2026)","journal-title":"Comput Sci Rev"},{"key":"25_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.112715","volume":"162","author":"S Samy","year":"2025","unstructured":"Samy, S., Durairaj, P., Ali, A., et al.: Secure fuzzy-based H\u221e consensus control for nonlinear multi-agent systems under quantized sampled-data mechanism and its applications. Eng. Appl. Artif. Intell. 162, 112715 (2025)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"25_CR31","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1109\/CCWC.2018.8301694","volume-title":"2018 IEEE 8th Annual Computing and Communication Workshop and Conference (CCWC)","author":"J Yin","year":"2018","unstructured":"Yin, J., Ali, R., Li, L., Ma, W., Ali, A.: Edge network model based on double dimension. In: 2018 IEEE 8th Annual Computing and Communication Workshop and Conference (CCWC), pp. 341\u2013346. IEEE, Piscataway, NJ, USA (2018)"},{"key":"25_CR32","first-page":"1","volume-title":"2017 International Conference on Electrical Engineering (ICEE)","author":"HMY Naeem","year":"2017","unstructured":"Naeem, H.M.Y., Mahmood, A.: Robust and optimal control of longitudinal dynamics of automotive vehicle. In: 2017 International Conference on Electrical Engineering (ICEE), pp. 1\u20136. IEEE, Piscataway, NJ, USA (2017)"},{"issue":"6","key":"25_CR33","doi-asserted-by":"publisher","first-page":"1133","DOI":"10.1177\/09544070211037468","volume":"236","author":"HMY Naeem","year":"2022","unstructured":"Naeem, H.M.Y., et al.: Eco-driving control of electric vehicle with battery dynamic model and multiple traffic signals. Proc. Inst. Mech. Eng., Part D: J. Automob. Eng. 236(6), 1133\u20131143 (2022)","journal-title":"Proc. Inst. Mech. Eng., Part D: J. Automob. Eng."},{"key":"25_CR34","doi-asserted-by":"publisher","first-page":"2398","DOI":"10.1109\/CDC.2013.6760239","volume-title":"52nd IEEE Conference on Decision and Control","author":"C Amato","year":"2013","unstructured":"Amato, C., Chowdhary, G., Geramifard, A., \u00dcre, N.K., Kochenderfer, M.J.: Decentralized control of partially observable Markov decision processes. In: 52nd IEEE Conference on Decision and Control, pp. 2398\u20132405. IEEE, Piscataway, NJ, USA (2013)"},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. arXiv preprint https:\/\/arxiv.org\/abs\/1409.1259 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"25_CR36","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 807--814 (2010)"},{"key":"25_CR37","doi-asserted-by":"publisher","first-page":"24611","DOI":"10.52202\/068431-1787","volume":"35","author":"C Yu","year":"2022","unstructured":"Yu, C., et al.: The surprising effectiveness of PPO in cooperative multi-agent games. Adv. Neural Inf. Proces. Syst. 35, 24611\u201324624 (2022)","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"25_CR38","unstructured":"Ackermann, J., Gabler, V., Osa, T., Sugiyama, M.: Reducing overestimation bias in multi-agent domains using double centralized critics. arXiv preprint https:\/\/arxiv.org\/abs\/1910.01465 (2019)"}],"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\/978-981-92-3381-6_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T20:15:11Z","timestamp":1784405711000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3381-6_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"ISBN":["9789819233809","9789819233816"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3381-6_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"19 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"}}]}}