{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:15:33Z","timestamp":1777655733916,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819722525","type":"print"},{"value":"9789819722532","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-2253-2_14","type":"book-chapter","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T10:02:11Z","timestamp":1713952931000},"page":"171-183","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards Cost-Efficient Federated Multi-agent RL with\u00a0Learnable Aggregation"],"prefix":"10.1007","author":[{"given":"Yi","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Sen","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zhi","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Xuwei","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Stano","family":"Funiak","sequence":"additional","affiliation":[]},{"given":"Jiajun","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,4,25]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Abegaz, M., Erbad, A., Nahom, H., Albaseer, A., Abdallah, M., Guizani, M.: Multi-agent federated reinforcement learning for resource allocation in UAV-enabled internet of medical things networks. IoT-J (2023)","DOI":"10.36227\/techrxiv.23153171"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Bottou, L., Curtis, F.E., Nocedal, J.: Optimization methods for large-scale machine learning. SIAM (2018)","DOI":"10.1137\/16M1080173"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Chaudhuri, R., Mukherjee, K., Narayanam, R., Vallam, R.D.: Collaborative reinforcement learning framework to model evolution of cooperation in sequential social dilemmas. In: PAKDD (2021)","DOI":"10.1007\/978-3-030-75762-5_2"},{"key":"14_CR4","unstructured":"Chen, T., Zhang, K., Giannakis, G.B., Ba\u015far, T.: Communication-efficient policy gradient methods for distributed reinforcement learning. TCNS (2021)"},{"key":"14_CR5","unstructured":"Christianos, F., Papoudakis, G., Rahman, A., Albrecht, S.V.: Scaling multi-agent reinforcement learning with selective parameter sharing. In: ICML (2021)"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Du, X., Wang, J., Chen, S.: Multi-agent meta-reinforcement learning with coordination and reward shaping for traffic signal control. In: PAKDD (2023)","DOI":"10.1007\/978-3-031-33377-4_27"},{"key":"14_CR7","unstructured":"Foerster, J., Assael, I.A., De\u00a0Freitas, N., Whiteson, S.: Learning to communicate with deep multi-agent reinforcement learning. In: NeurIPS (2016)"},{"key":"14_CR8","unstructured":"Hu, S., Zhu, F., Chang, X., Liang, X.: UPDeT: universal multi-agent reinforcement learning via policy decoupling with transformers. In: ICLR (2021)"},{"key":"14_CR9","unstructured":"Jin, H., Peng, Y., Yang, W., Wang, S., Zhang, Z.: Federated reinforcement learning with environment heterogeneity. In: AISTATS (2022)"},{"key":"14_CR10","unstructured":"Karimireddy, S.P., Kale, S., Mohri, M., Reddi, S., Stich, S., Suresh, A.T.: Scaffold: stochastic controlled averaging for federated learning. In: ICML (2020)"},{"key":"14_CR11","unstructured":"Khodadadian, S., Sharma, P., Joshi, G., Maguluri, S.T.: Federated reinforcement learning: linear speedup under Markovian sampling. In: ICML (2022)"},{"key":"14_CR12","unstructured":"Kuba, J.G., Chen, R., Wen, M., Wen, Y., Sun, F., Wang, J., Yang, Y.: Trust region policy optimisation in multi-agent reinforcement learning. In: ICLR (2022)"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Li, Q., Peng, Z., Feng, L., Zhang, Q., Xue, Z., Zhou, B.: MetaDrive: composing diverse driving scenarios for generalizable reinforcement learning. TPAMI (2022)","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"14_CR14","unstructured":"Li, T., Sahu, A.K., Zaheer, M., Sanjabi, M., Talwalkar, A., Smith, V.: Federated optimization in heterogeneous networks. In: MLSys (2020)"},{"key":"14_CR15","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: NeurIPS (2017)"},{"key":"14_CR16","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., y\u00a0Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: AISTATS (2017)"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Mo, J., Xie, H.: A multi-player MAB approach for distributed selection problems. In: PAKDD (2023)","DOI":"10.1007\/978-3-031-33377-4_19"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Pang, Y., Zhang, H., Deng, J.D., Peng, L., Teng, F.: Rule-based collaborative learning with heterogeneous local learning models. In: PAKDD (2022)","DOI":"10.1007\/978-3-031-05933-9_50"},{"key":"14_CR19","unstructured":"Peng, Z., Hui, K.M., Liu, C., Zhou, B.: Learning to simulate self-driven particles system with coordinated policy optimization. In: NeurIPS (2021)"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Pinto Neto, E.C., Sadeghi, S., Zhang, X., Dadkhah, S.: Federated reinforcement learning in IoT: applications, opportunities and open challenges. Appl. Sci. (2023)","DOI":"10.3390\/app13116497"},{"key":"14_CR21","unstructured":"Rashid, T., Samvelyan, M., De\u00a0Witt, C.S., Farquhar, G., Foerster, J., Whiteson, S.: Monotonic value function factorisation for deep multi-agent reinforcement learning. JMLR (2020)"},{"key":"14_CR22","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv:1707.06347 (2017)"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Song, Y., Chang, H.H., Liu, L.: Federated dynamic spectrum access through multi-agent deep reinforcement learning. In: GLOBECOM (2022)","DOI":"10.1109\/GLOBECOM48099.2022.10001688"},{"key":"14_CR24","unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning. arXiv:1706.05296 (2017)"},{"key":"14_CR25","unstructured":"Wang, J., Joshi, G.: Cooperative SGD: a unified framework for the design and analysis of local-update SGD algorithms. JMLR (2021)"},{"key":"14_CR26","unstructured":"Wang, J., Liu, Q., Liang, H., Joshi, G., Poor, H.V.: Tackling the objective inconsistency problem in heterogeneous federated optimization. In: NeurIPS (2020)"},{"key":"14_CR27","unstructured":"Wen, M., et al.: Multi-agent reinforcement learning is a sequence modeling problem. Front. Comput. Sci. (2022)"},{"key":"14_CR28","unstructured":"de\u00a0Witt, C.S., et al.: Is independent learning all you need in the starcraft multi-agent challenge? arXiv:2011.09533 (2020)"},{"key":"14_CR29","unstructured":"Xu, X., Li, R., Zhao, Z., Zhang, H.: The gradient convergence bound of federated multi-agent reinforcement learning with efficient communication. TWC (2023)"},{"key":"14_CR30","unstructured":"Yu, C., Velu, A., Vinitsky, E., Gao, J., Wang, Y., Bayen, A., Wu, Y.: The surprising effectiveness of PPO in cooperative multi-agent games. In: NeurIPS (2022)"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Zhou, X., Matsubara, S., Liu, Y., Liu, Q.: Bribery in rating systems: a game-theoretic perspective. In: PAKDD (2022)","DOI":"10.1007\/978-3-031-05981-0_6"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-2253-2_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T23:12:31Z","timestamp":1714000351000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2253-2_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819722525","9789819722532"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2253-2_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"25 April 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taipei","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taiwan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 May 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 May 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}