{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T23:46:18Z","timestamp":1742946378077,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031383328"},{"type":"electronic","value":"9783031383335"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-38333-5_6","type":"book-chapter","created":{"date-parts":[[2023,7,20]],"date-time":"2023-07-20T11:02:28Z","timestamp":1689850948000},"page":"54-64","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Learning from\u00a0Peers for\u00a0Distributed Actor-Critic Algorithms"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2261-8288","authenticated-orcid":false,"given":"Chandreyee","family":"Bhowmick","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9801-8417","authenticated-orcid":false,"given":"Jiani","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0923-6293","authenticated-orcid":false,"given":"Xenofon","family":"Koutsoukos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,21]]},"reference":[{"unstructured":"Anguita, D., Ghio, A., Oneto, L., Parra, X., Reyes-Ortiz, J.L.: A public domain dataset for human activity recognition using smartphones. In: 21st European Symposium on Artificial Neural Networks, ESANN, Bruges, Belgium, 24\u201326 April 2013 (2013)","key":"6_CR1"},{"issue":"4","key":"6_CR2","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1109\/MIS.2020.2988604","volume":"35","author":"Y Chen","year":"2020","unstructured":"Chen, Y., Qin, X., Wang, J., Yu, C., Gao, W.: FedHealth: a federated transfer learning framework for wearable healthcare. IEEE Intell. Syst. 35(4), 83\u201393 (2020)","journal-title":"IEEE Intell. Syst."},{"issue":"3","key":"6_CR3","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1109\/MSP.2012.2231991","volume":"30","author":"AH Sayed","year":"2013","unstructured":"Sayed, A.H., Tu, S.-Y., Chen, J., Zhao, X., Towfic, Z.J.: Diffusion strategies for adaptation and learning over networks: an examination of distributed strategies and network behavior. IEEE Signal Process. Mag. 30(3), 155\u2013171 (2013)","journal-title":"IEEE Signal Process. Mag."},{"issue":"5","key":"6_CR4","doi-asserted-by":"publisher","first-page":"1260","DOI":"10.1109\/TAC.2014.2368731","volume":"60","author":"SV Macua","year":"2014","unstructured":"Macua, S.V., Chen, J., Zazo, S., Sayed, A.H.: Distributed policy evaluation under multiple behavior strategies. IEEE Trans. Autom. Control 60(5), 1260\u20131274 (2014)","journal-title":"IEEE Trans. Autom. Control"},{"unstructured":"McMahan, H.B., Moore, E., Ramage, D., Ag\u00fcera y Arcas, B.: Federated learning of deep networks using model averaging. CoRR, abs\/1602.05629 (2016)","key":"6_CR5"},{"issue":"7","key":"6_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3543846","volume":"55","author":"MM Afsar","year":"2022","unstructured":"Afsar, M.M., Crump, T., Far, B.: Reinforcement learning based recommender systems: a survey. ACM Comput. Surv. 55(7), 1\u201338 (2022)","journal-title":"ACM Comput. Surv."},{"doi-asserted-by":"crossref","unstructured":"Prabuchandran, K.J., Hemanth Kumar, A.N., Bhatnagar, S.: Multi-agent reinforcement learning for traffic signal control. In: 17th International IEEE Conference on Intelligent Transportation Systems (ITSC), pp. 2529\u20132534. IEEE (2014)","key":"6_CR7","DOI":"10.1109\/ITSC.2014.6958095"},{"issue":"6","key":"6_CR8","doi-asserted-by":"publisher","first-page":"2192","DOI":"10.1109\/TNNLS.2018.2801880","volume":"29","author":"W Liu","year":"2018","unstructured":"Liu, W., Zhuang, P., Liang, H., Peng, J., Huang, Z.: Distributed economic dispatch in microgrids based on cooperative reinforcement learning. IEEE Trans. Neural Netw. Learn. Syst. 29(6), 2192\u20132203 (2018)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"doi-asserted-by":"crossref","unstructured":"Zhang, K., Yang, Z., Liu, H., Zhang, T., Basar, T.: Fully decentralized multi-agent reinforcement learning with networked agents. In: International Conference on Machine Learning, pp. 5872\u20135881. PMLR (2018)","key":"6_CR9","DOI":"10.1109\/CDC.2018.8619581"},{"unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, vol. 30 (2017)","key":"6_CR10"},{"issue":"7","key":"6_CR11","doi-asserted-by":"publisher","first-page":"1848","DOI":"10.1109\/TSP.2013.2241057","volume":"61","author":"S Kar","year":"2013","unstructured":"Kar, S., Moura, J.M.F., Poor, H.V.: QD-learning: a collaborative distributed strategy for multi-agent reinforcement learning through Consensus + Innovations. IEEE Trans. Signal Process. 61(7), 1848\u20131862 (2013)","journal-title":"IEEE Trans. Signal Process."},{"unstructured":"Macua, S.V., Tukiainen, A., Hern\u00e1ndez, D.G.-O., Baldazo, D., de\u00a0Cote, E.M., Zazo, S.: Diff-DAC: distributed actor-critic for multitask deep reinforcement learning. arXiv preprint arXiv:1710.10363 (2017)","key":"6_CR12"},{"key":"6_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2020.106959","volume":"192","author":"D Yan","year":"2021","unstructured":"Yan, D., et al.: Multi-task deep reinforcement learning for intelligent multi-zone residential HVAC control. Electr. Power Syst. Res. 192, 106959 (2021)","journal-title":"Electr. Power Syst. Res."},{"doi-asserted-by":"crossref","unstructured":"Zhang, Q., et al.: Multi-task fusion via reinforcement learning for long-term user satisfaction in recommender systems. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 4510\u20134520 (2022)","key":"6_CR14","DOI":"10.1145\/3534678.3539040"},{"issue":"3","key":"6_CR15","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/MSP.2020.2966273","volume":"37","author":"R Nassif","year":"2020","unstructured":"Nassif, R., Vlaski, S., Richard, C., Chen, J., Sayed, A.H.: Multitask learning over graphs: an approach for distributed, streaming machine learning. IEEE Signal Process. Mag. 37(3), 14\u201325 (2020)","journal-title":"IEEE Signal Process. Mag."},{"unstructured":"Konstantinov, N., Lampert, C.: Robust learning from untrusted sources. In: International Conference on Machine Learning, pp. 3488\u20133498. PMLR (2019)","key":"6_CR16"},{"doi-asserted-by":"crossref","unstructured":"Lin, Y., Gade, S., Sandhu, R., Liu, J.: Toward resilient multi-agent actor-critic algorithms for distributed reinforcement learning. In: 2020 American Control Conference (ACC), pp. 3953\u20133958. IEEE (2020)","key":"6_CR17","DOI":"10.23919\/ACC45564.2020.9147381"},{"unstructured":"Blundell, C., Cornebise, J., Kavukcuoglu, K., Wierstra, D.: Weight uncertainty in neural network. In: International Conference on Machine Learning, pp. 1613\u20131622. PMLR (2015)","key":"6_CR18"},{"doi-asserted-by":"crossref","unstructured":"Shui, C., Abbasi, M., Robitaille, L.-\u00c9., Wang, B., Gagn\u00e9, C.: A principled approach for learning task similarity in multitask learning. In: IJCAI (2019)","key":"6_CR19","DOI":"10.24963\/ijcai.2019\/478"},{"unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)","key":"6_CR20"},{"unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning, pp. 1587\u20131596. PMLR (2018)","key":"6_CR21"},{"issue":"2","key":"6_CR22","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1137\/16M1080173","volume":"60","author":"L Bottou","year":"2018","unstructured":"Bottou, L., Curtis, F.E., Nocedal, J.: Optimization methods for large-scale machine learning. SIAM Rev. 60(2), 223\u2013311 (2018)","journal-title":"SIAM Rev."},{"unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)","key":"6_CR23"},{"unstructured":"Wu, Y.F., Zhang, W., Xu, P., Gu, Q.: A finite-time analysis of two time-scale actor-critic methods. In: Advances in Neural Information Processing Systems, vol. 33, pp. 17617\u201317628 (2020)","key":"6_CR24"},{"doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MuJoCo: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033. IEEE (2012)","key":"6_CR25","DOI":"10.1109\/IROS.2012.6386109"},{"unstructured":"Brockman, G., et al.: OpenAI Gym.arXiv preprint arXiv:1606.01540 (2016)","key":"6_CR26"},{"unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)","key":"6_CR27"},{"unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)","key":"6_CR28"}],"container-title":["Lecture Notes in Networks and Systems","Distributed Computing and Artificial Intelligence, 20th International Conference"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-38333-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,20]],"date-time":"2023-07-20T11:04:53Z","timestamp":1689851093000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-38333-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031383328","9783031383335"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-38333-5_6","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"21 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Distributed Computing and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guimaraes","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dcai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.dcai-conference.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}