{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T08:10:59Z","timestamp":1778487059690,"version":"3.51.4"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s10994-025-06967-y","type":"journal-article","created":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T07:13:25Z","timestamp":1776237205000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Boosting Efficient Experience Exchange in Sparse-Reward Multi-Agent Reinforcement Learning"],"prefix":"10.1007","volume":"115","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7976-1715","authenticated-orcid":false,"given":"Jianan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1637-1511","authenticated-orcid":false,"given":"Zaipeng","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9610-9597","authenticated-orcid":false,"given":"Nuo","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1903-7476","authenticated-orcid":false,"given":"Juguang","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8174-1772","authenticated-orcid":false,"given":"WenZhan","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,15]]},"reference":[{"key":"6967_CR1","doi-asserted-by":"crossref","unstructured":"Cayci, S., & Eryilmaz, A. (2023). Provably robust temporal difference learning for heavy-tailed rewards. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, (Vol. 36, pp. 25693\u201325711).","DOI":"10.52202\/075280-1117"},{"key":"6967_CR2","doi-asserted-by":"publisher","unstructured":"Chen, Y., Yang, K., Tao, J., & Lyu, J. (2025). Novelty-guided data reuse for efficient and diversified multi-agent reinforcement learning. In Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025, February 25 - March 4, 608 2025, Philadelphia, PA, USA, pp. 15930\u201315938. https:\/\/doi.org\/10.1609\/AAAI.V39I15.33749","DOI":"10.1609\/AAAI.V39I15.33749"},{"key":"6967_CR3","doi-asserted-by":"crossref","unstructured":"Ellis, B., Cook, J., Moalla, S., Samvelyan, M., Sun, M., Mahajan, A., & Whiteson, S. (2023). SMACv2: An improved benchmark for cooperative multi-agent reinforcement learning. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, (Vol. 36, pp. 37567\u201337593) .","DOI":"10.52202\/075280-1634"},{"issue":"4","key":"6967_CR4","doi-asserted-by":"publisher","first-page":"3473","DOI":"10.1109\/TMC.2024.3509680","volume":"24","author":"L Feng","year":"2025","unstructured":"Feng, L., Jiang, X., Sun, Y., Niyato, D., Zhou, Y., Gu, S., & Zhou, F. (2025). Resource allocation for metaverse experience optimization: A multi-objective multi-agent evolutionary reinforcement learning approach. IEEE Transactions on Mobile Computing,24(4), 3473\u20133488. https:\/\/doi.org\/10.1109\/TMC.2024.3509680","journal-title":"IEEE Transactions on Mobile Computing"},{"issue":"5","key":"6967_CR6","doi-asserted-by":"publisher","first-page":"3552","DOI":"10.1109\/TMC.2024.3514124","volume":"24","author":"S Ge","year":"2025","unstructured":"Ge, S., Zhou, X., & Qiu, T. (2025). R2Pricing: A MARL-based pricing strategy to maximize revenue in mod systems with ridesharing and repositioning. IEEE Transactions on Mobile Computing,24(5), 3552\u20133566. https:\/\/doi.org\/10.1109\/TMC.2024.3514124","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"6967_CR5","doi-asserted-by":"crossref","unstructured":"Gerstgrasser, M., Danino, T., & Keren, S. (2023). Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning. In Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2023, London, United Kingdom, 29 May 2023 - 2 June 2023, pp 2433\u20132435.","DOI":"10.65109\/YQSX9164"},{"key":"6967_CR8","doi-asserted-by":"crossref","unstructured":"Hu, X., Zhao, J., Zhou, W., Feng, R., & Li, H. (2023). DIFFER: Decomposing individual reward for fair experience replay in multi-agent reinforcement learning. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, (Vol. 36, pp. 75048\u201375066).","DOI":"10.52202\/075280-3281"},{"key":"6967_CR7","unstructured":"Hu, Z., Zhang, Z., Li, H., Chen, C., Ding, H., & Wang, Z. (2024). Attention-guided contrastive role representations for multi-agent reinforcement learning. In Proceedings of the 12th International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024."},{"key":"6967_CR9","unstructured":"Jeon, J., Kim, W., Jung, W., & Sung, Y. (2022). MASER: Multi-agent reinforcement learning with subgoals generated from experience replay buffer. In Proceedings of the 39th International Conference on Machine Learning, ICML 2022, Baltimore, Maryland, USA, July 17-23, 2022, pp. 10041\u201310052."},{"key":"6967_CR10","doi-asserted-by":"publisher","unstructured":"Kurach, K., Raichuk, A., Sta\u0144czyk, P., Zaj\u0105c, M., Bachem, O., Espeholt, L., & Gelly, S. (2020). Google research football: A novel reinforcement learning environment. In Proceedings of the 34th AAAI Conference on Artificial Intelligence, AAAI 2020, New York, NY, USA, February 7-12, 2020, (Vol. 34, pp. 4501\u20134510). https:\/\/doi.org\/10.1609\/AAAI.V34I04.5878","DOI":"10.1609\/AAAI.V34I04.5878"},{"key":"6967_CR12","unstructured":"Li, X., Pan, L., & Zhang, J. (2024). Kaleidoscope: Learnable masks for heterogeneous multi-agent reinforcement learning. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024."},{"key":"6967_CR11","unstructured":"Liu, B., Pu, Z., Pan, Y., Yi, J., Liang, Y., & Zhang, D. (2023). Lazy agents: A new perspective on solving sparse reward problem in multi-agent reinforcement learning. In Proceedings of the 40th International Conference on Machine Learning, ICML 2023, Honolulu, Hawaii, USA, July 23-29, 2023, pp. 21937\u201321950."},{"key":"6967_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/J.NEUNET.2025.107254","volume":"186","author":"X Mu","year":"2025","unstructured":"Mu, X., Zhuo, H. H., Chen, C., Zhang, K., Yu, C., & Hao, J. (2025). Hierarchical task network-enhanced multi-agent reinforcement learning: Toward efficient cooperative strategies. Neural Networks,186, 107254. https:\/\/doi.org\/10.1016\/J.NEUNET.2025.107254","journal-title":"Neural Networks"},{"key":"6967_CR14","doi-asserted-by":"publisher","unstructured":"Oliehoek, F. A., & Amato, C. (2016). A concise introduction to decentralized POMDPs. Springer Briefs in Intelligent Systems. https:\/\/doi.org\/10.1007\/978-3-319-28929-8","DOI":"10.1007\/978-3-319-28929-8"},{"issue":"11","key":"6967_CR15","doi-asserted-by":"publisher","first-page":"13677","DOI":"10.1007\/S10489-022-04105-Y","volume":"53","author":"A Oroojlooy","year":"2023","unstructured":"Oroojlooy, A., & Hajinezhad, D. (2023). A review of cooperative multi-agent deep reinforcement learning. Applied Intelligence,53(11), 13677\u201313722. https:\/\/doi.org\/10.1007\/S10489-022-04105-Y","journal-title":"Applied Intelligence"},{"key":"6967_CR16","unstructured":"Rashid, T., Samvelyan, M., Witt, C. S., Farquhar, G., Foerster, J. N., & Whiteson, S. (2018). QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10-15, 2018, (Vol. 80, pp. 4292\u20134301)."},{"key":"6967_CR18","doi-asserted-by":"crossref","unstructured":"Samvelyan, M., Rashid, T., De Witt, C. S., Farquhar, G., Nardelli, N., Rudner, T. G., & Whiteson, S. (2019). The starcraft multi-agent challenge. In Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems,  AAMAS 2019, Montreal, QC, Canada, May 13-17, 2019, pp. 2186\u20132188.","DOI":"10.65109\/LVZZ5205"},{"key":"6967_CR17","unstructured":"Schaul, T., Quan, J., Antonoglou, I., & Silver, D. (2016). Prioritized experience replay. In Proceedings of the 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016."},{"key":"6967_CR19","unstructured":"Shao, J., Zhang, H., Qu, Y., Liu, C., He, S., Jiang, Y., & Ji, X. (2023). Complementary attention for multi-agent reinforcement learning. In Proceedings of the 40th International Conference on Machine Learning, ICML 2023, Hawaii, USA, 23-29 July 2023, (Vol. 202, pp. 30776\u201330793)."},{"key":"6967_CR20","unstructured":"Trott, A., Zheng, S., Xiong, C., & Socher, R. (2019). Keeping your distance: Solving sparse reward tasks using self-balancing shaped rewards. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, pp. 10376\u201310386."},{"key":"6967_CR21","doi-asserted-by":"publisher","unstructured":"Xie, Z., Shen, S., Wang, Y., Qiao, C., Tang, B., & Song, W. (2026). ROCO: Role-oriented communication for efficient multi-agent reinforcement learning. Expert Systems with Applications, 297, 129421. https:\/\/doi.org\/10.1016\/j.eswa.2025.129421","DOI":"10.1016\/j.eswa.2025.129421"},{"key":"6967_CR22","doi-asserted-by":"publisher","unstructured":"Xu, P., Zhang, J., & Huang, K. (2024). Population-based diverse exploration for sparse-reward multi-agent tasks. In Proceedings of the 33rd International Joint Conference on Artificial Intelligence, IJCAI 2024, Jeju, South Korea, August 3-9, 2024, pp. 283\u2013291. https:\/\/doi.org\/10.24963\/ijcai.2024\/32","DOI":"10.24963\/ijcai.2024\/32"},{"key":"6967_CR23","doi-asserted-by":"publisher","unstructured":"Xu, P., Zhang, J., Yin, Q., Yu, C., Yang, Y., & Huang, K. (2023). Subspace-aware exploration for sparse-reward multi-agent tasks. In Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023, Washington, DC, USA, February 7-14, 2023, (Vol. 37, pp. 11717\u201311725). https:\/\/doi.org\/10.1609\/AAAI.V37I10.26384","DOI":"10.1609\/AAAI.V37I10.26384"},{"key":"6967_CR24","doi-asserted-by":"publisher","unstructured":"Yu, X., Shi, R., Feng, P., Tian, Y., Li, S., Liao, S., & Wu, W. (2024). Leveraging partial symmetry for multi-agent reinforcement learning. In Proceedings of the 38th AAAI Conference on Artificial Intelligence, AAAI 2024, Vancouver, Canada, February 20-27, 2024, vol. 38, pp. 17583\u201317590. https:\/\/doi.org\/10.1609\/AAAI.V38I16.29709","DOI":"10.1609\/AAAI.V38I16.29709"},{"key":"6967_CR25","doi-asserted-by":"publisher","unstructured":"Yu, Y., Yin, Q., Zhang, J., Xu, P., & Huang, K. (2024). ADMN: Agent-driven modular network for dynamic parameter sharing in cooperative multi-agent reinforcement learning. In Proceedings of the 33rd International Joint Conference on Artificial Intelligence, IJCAI 2024, Jeju, South Korea, August 3-9, 2024, pp. 302\u2013310. https:\/\/doi.org\/10.24963\/ijcai.2024\/34","DOI":"10.24963\/ijcai.2024\/34"},{"issue":"1","key":"6967_CR26","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/S10458-023-09633-6","volume":"38","author":"C Zhu","year":"2024","unstructured":"Zhu, C., Dastani, M., & Wang, S. (2024). A survey of multi-agent deep reinforcement learning with communication. Autonomous Agents and Multi-Agent Systems,38(1), 4. https:\/\/doi.org\/10.1007\/S10458-023-09633-6","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"issue":"12","key":"6967_CR27","doi-asserted-by":"publisher","first-page":"13639","DOI":"10.1109\/TMC.2024.3437376","volume":"23","author":"S Zhu","year":"2024","unstructured":"Zhu, S., Han, G., Lin, C., & Tao, Q. (2024). Underwater target tracking based on hierarchical software-defined multi-AUV reinforcement learning: A multi-AUV advantage-attention actor-critic approach. IEEE Transactions on Mobile Computing,23(12), 13639\u201313653. https:\/\/doi.org\/10.1109\/TMC.2024.3437376","journal-title":"IEEE Transactions on Mobile Computing"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06967-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-025-06967-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06967-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T07:42:47Z","timestamp":1778485367000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-025-06967-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":27,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["6967"],"URL":"https:\/\/doi.org\/10.1007\/s10994-025-06967-y","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"31 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 September 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 December 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"95"}}