{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T01:54:34Z","timestamp":1781574874721,"version":"3.54.5"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031083327","type":"print"},{"value":"9783031083334","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-08333-4_22","type":"book-chapter","created":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T11:52:13Z","timestamp":1655380333000},"page":"270-281","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["MTMA-DDPG: A Deep Deterministic Policy Gradient Reinforcement Learning for Multi-task Multi-agent Environments"],"prefix":"10.1007","author":[{"given":"Karim","family":"Hamadeh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julia","family":"El Zini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joudi","family":"Hajar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mariette","family":"Awad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,6,10]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Bram, T., Brunner, G., Richter, O., Wattenhofer, R.: Attentive multi-task deep reinforcement learning. arXiv preprint arXiv:1907.02874 (2019)","DOI":"10.1007\/978-3-030-46133-1_9"},{"key":"22_CR2","unstructured":"Crawshaw, M.: Multi-task learning with deep neural networks: a survey. arXiv preprint arXiv:2009.09796 (2020)"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"El Bsat, S., Ammar, H.B., Taylor, M.E.: Scalable multitask policy gradient reinforcement learning. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.10942"},{"key":"22_CR4","unstructured":"Iqbal, S.: Maddpg-pytorch. https:\/\/github.com\/shariqiqbal2810\/maddpg-pytorch (2017)"},{"key":"22_CR5","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"22_CR6","unstructured":"Liu, X., Li, L., Hsieh, P.C., Xie, M., Ge, Y., Chen, R.: Developing multi-task recommendations with long-term rewards via policy distilled reinforcement learning. arXiv preprint arXiv:2001.09595 (2020)"},{"key":"22_CR7","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. arXiv preprint arXiv:1706.02275 (2017)"},{"key":"22_CR8","unstructured":"Macua, S.V., Tukiainen, A., Hern\u00e1ndez, D.G.O., Baldazo, D., de Cote, E.M., Zazo, S.: Diff-dac: Distributed actor-critic for average multitask deep reinforcement learning. arXiv preprint arXiv:1710.10363 (2017)"},{"key":"22_CR9","unstructured":"Omidshafiei, S., Pazis, J., Amato, C., How, J.P., Vian, J.: Deep decentralized multi-task multi-agent reinforcement learning under partial observability. In: International Conference on Machine Learning, pp. 2681\u20132690. PMLR (2017)"},{"key":"22_CR10","unstructured":"Papoudakis, G., Christianos, F., Sch\u00e4fer, L., Albrecht, S.V.: Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks (2021)"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Pinto, L., Gupta, A.: Learning to push by grasping: Using multiple tasks for effective learning. In: 2017 IEEE international conference on robotics and automation (ICRA), pp. 2161\u20132168. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989249"},{"key":"22_CR12","unstructured":"Pitis, S., Chan, H., Zhao, S., Stadie, B., Ba, J.: Maximum entropy gain exploration for long horizon multi-goal reinforcement learning. In: International Conference on Machine Learning, pp. 7750\u20137761. PMLR (2020)"},{"key":"22_CR13","unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)"},{"key":"22_CR14","unstructured":"Teh, Y.W., et al.: Distral: robust multitask reinforcement learning. arXiv preprint arXiv:1707.04175 (2017)"},{"key":"22_CR15","first-page":"8907","volume":"31","author":"R Tutunov","year":"2018","unstructured":"Tutunov, R., Kim, D., Bou Ammar, H.: Distributed multitask reinforcement learning with quadratic convergence. Adv. Neural Inf. Process. Syst. 31, 8907\u20138916 (2018)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"9","key":"22_CR16","doi-asserted-by":"publisher","first-page":"1363","DOI":"10.3390\/electronics9091363","volume":"9","author":"N Vithayathil Varghese","year":"2020","unstructured":"Vithayathil Varghese, N., Mahmoud, Q.H.: A survey of multi-task deep reinforcement learning. Electronics 9(9), 1363 (2020)","journal-title":"Electronics"},{"key":"22_CR17","unstructured":"Wang, R.E., Everett, M., How, J.P.: R-MADDPG for partially observable environments and limited communication. arXiv preprint arXiv:2002.06684 (2020)"},{"key":"22_CR18","unstructured":"Yu, C., Velu, A., Vinitsky, E., Wang, Y., Bayen, A., Wu, Y.: The surprising effectiveness of mappo in cooperative, multi-agent games. arXiv preprint arXiv:2103.01955 (2021)"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, R., Zhu, Q.: Consensus-based transfer linear support vector machines for decentralized multi-task multi-agent learning. In: 2018 52nd Annual Conference on Information Sciences and Systems (CISS), pp. 1\u20136. IEEE (2018)","DOI":"10.1109\/CISS.2018.8362195"},{"key":"22_CR20","unstructured":"Zhao, R., Sun, X., Tresp, V.: Maximum entropy-regularized multi-goal reinforcement learning. In: International Conference on Machine Learning, pp. 7553\u20137562. PMLR (2019)"}],"container-title":["IFIP Advances in Information and Communication Technology","Artificial Intelligence Applications and Innovations"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-08333-4_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T01:41:04Z","timestamp":1781574064000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-08333-4_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031083327","9783031083334"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-08333-4_22","relation":{},"ISSN":["1868-4238","1868-422X"],"issn-type":[{"value":"1868-4238","type":"print"},{"value":"1868-422X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"10 June 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Artificial Intelligence Applications and Innovations","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hersonissos","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 June 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 June 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aiai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ifipaiai.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}