{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T14:27:50Z","timestamp":1758810470989,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030640958"},{"type":"electronic","value":"9783030640965"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-64096-5_4","type":"book-chapter","created":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T00:30:27Z","timestamp":1606264227000},"page":"40-54","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["D3PG: Decomposed Deep Deterministic Policy Gradient for Continuous Control"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1875-1772","authenticated-orcid":false,"given":"Yinzhao","family":"Dong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4371-3663","authenticated-orcid":false,"given":"Chao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8937-1515","authenticated-orcid":false,"given":"Hongwei","family":"Ge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,25]]},"reference":[{"issue":"2","key":"4_CR1","first-page":"156","volume":"38","author":"L Bu","year":"2008","unstructured":"Bu, L., Babu, R., De Schutter, B., et al.: A comprehensive survey of multiagent reinforcement learning. IEEE TSMC Part C 38(2), 156\u2013172 (2008)","journal-title":"IEEE TSMC Part C"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Busoniu, L., De Schutter, B., Babuska, R.: Decentralized reinforcement learning control of a robotic manipulator. In: 2006 9th ICARCV, pp. 1\u20136 (2006)","DOI":"10.1109\/ICARCV.2006.345351"},{"key":"4_CR3","unstructured":"Dong, Y., Yu, C., Weng, P., Maustafa, A., Cheng, H., Ge, H.: Decomposed deep reinforcement learning for robotic control. In: Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems, pp. 1834\u20131836 (2020)"},{"key":"4_CR4","unstructured":"Duan, Y., Chen, X., Houthooft, R., Schulman, J., Abbeel: Benchmarking deep reinforcement learning for continuous control. In: ICML, pp. 1329\u20131338 (2016)"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Dziomin, U., Kabysh, A., Golovko, V., Stetter, R.: A multi-agent reinforcement learning approach for the efficient control of mobile robot. In: 2013 IEEE 7th IDAACS, vol. 2, pp. 867\u2013873 (2013)","DOI":"10.1109\/IDAACS.2013.6663051"},{"key":"4_CR6","unstructured":"Foerster, J., Assael, I.A., de Freitas, N., Whiteson, S.: Learning to communicate with deep multi-agent reinforcement learning. In: NIPS, pp. 2137\u20132145 (2016)"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Foerster, J.N., Farquhar, G., Afouras, T., et al.: Counterfactual multi-agent policy gradients. In: AAAI, pp. 7254\u20137264 (2018)","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"4_CR8","unstructured":"Guestrin, C., Lagoudakis, M., Parr, R.: Coordinated reinforcement learning. In: ICML, vol. 2, pp. 227\u2013234 (2002)"},{"key":"4_CR9","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1007\/978-3-319-71682-4_5","volume-title":"Autonomous Agents and Multiagent Systems","author":"JK Gupta","year":"2017","unstructured":"Gupta, J.K., Egorov, M., Kochenderfer, M.: Cooperative multi-agent control using deep reinforcement learning. In: Sukthankar, G., Rodriguez-Aguilar, J.A. (eds.) AAMAS 2017. LNCS (LNAI), vol. 10642, pp. 66\u201383. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-71682-4_5"},{"key":"4_CR10","unstructured":"Iqbal, S., Sha, F.: Actor-attention-critic for multi-agent reinforcement learning. arXiv preprint arXiv:1810.02912 (2018)"},{"key":"4_CR11","unstructured":"Jiang, J., Lu, Z.: Learning attentional communication for multi-agent cooperation. In: NIPS, pp. 7254\u20137264 (2018)"},{"issue":"1","key":"4_CR12","doi-asserted-by":"crossref","first-page":"39","DOI":"10.47839\/ijc.11.1.549","volume":"11","author":"A Kabysh","year":"2014","unstructured":"Kabysh, A., Golovko, V., Lipnickas, A.: Influence learning for multi-agent system based on reinforcement learning. Int. J. Comput. 11(1), 39\u201344 (2014)","journal-title":"Int. J. Comput."},{"key":"4_CR13","unstructured":"Kok, J.R., Vlassis, N.: Collaborative multiagent reinforcement learning by payoff propagation. J. Mach. Learn. Res. 7(Sep), 1789\u20131828 (2006)"},{"key":"4_CR14","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1007\/978-3-319-29339-4_24","volume-title":"RoboCup 2015: Robot World Cup XIX","author":"DL Leottau","year":"2015","unstructured":"Leottau, D.L., Ruiz-del-Solar, J., MacAlpine, P., Stone, P.: A study of layered learning strategies applied to individual behaviors in robot soccer. In: Almeida, L., Ji, J., Steinbauer, G., Luke, S. (eds.) RoboCup 2015. LNCS (LNAI), vol. 9513, pp. 290\u2013302. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-29339-4_24"},{"key":"4_CR15","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.artint.2017.12.001","volume":"256","author":"DL Leottau","year":"2018","unstructured":"Leottau, D.L., Ruiz-del Solar, J., Babu\u0161ka, R.: Decentralized reinforcement learning of robot behaviors. Artif. Intell. 256, 130\u2013159 (2018)","journal-title":"Artif. Intell."},{"key":"4_CR16","unstructured":"Leottau, D.L., Ruiz-del Solar, J.: An accelerated approach to decentralized reinforcement learning of the ball-dribbling behavior. In: Workshops at the Twenty-Ninth AAAI (2015)"},{"key":"4_CR17","unstructured":"Li, Y.: Deep reinforcement learning. arXiv preprint arXiv:1810.06339 (2018)"},{"key":"4_CR18","unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"4_CR19","unstructured":"Lowe, R., Wu, Y., Tamar, A., et al.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: NIPS, pp. 6379\u20136390 (2017)"},{"key":"4_CR20","unstructured":"Mao, H., Zhang, Z., et al.: Modelling the dynamic joint policy of teammates with attention multi-agent DDPG. In: AAMAS, pp. 1108\u20131116 (2019)"},{"key":"4_CR21","unstructured":"Martin, J.A., De Lope, H., et al.: A distributed reinforcement learning architecture for multi-link robots. In: 4th ICINCO, vol. 192, p. 197 (2007)"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Matignon, L., Laurent, G.J., Le Fort-Piat, N.: Design of semi-decentralized control laws for distributed-air-jet micromanipulators by reinforcement learning. In: 2009 IROS, pp. 3277\u20133283 (2009)","DOI":"10.1109\/IROS.2009.5353902"},{"key":"4_CR23","unstructured":"Mnih, V., Badia, A.P., et al.: Asynchronous methods for deep reinforcement learning. In: ICML, pp. 1928\u20131937 (2016)"},{"key":"4_CR24","unstructured":"Peng, P., Yuan, Q., et al.: Multiagent bidirectionally-coordinated nets for learning to play StarCraft combat games, p. 2. arXiv preprint arXiv:1703.10069 (2017)"},{"issue":"7\u20139","key":"4_CR25","doi-asserted-by":"publisher","first-page":"1180","DOI":"10.1016\/j.neucom.2007.11.026","volume":"71","author":"J Peters","year":"2008","unstructured":"Peters, J., Schaal, S.: Natural actor-critic. Neurocomputing 71(7\u20139), 1180\u20131190 (2008)","journal-title":"Neurocomputing"},{"key":"4_CR26","unstructured":"Rashid, T., Samvelyan, M., et al.: QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. In: ICML, pp. 4292\u20134301 (2018)"},{"key":"4_CR27","unstructured":"Sanchez-Gonzalez, A., Heess, N., et al.: Graph networks as learnable physics engines for inference and control. arXiv preprint arXiv:1806.01242 (2018)"},{"key":"4_CR28","unstructured":"Schulman, J., Levine, S., Abbeel, P., et al.: Trust region policy optimization. In: ICML, pp. 1889\u20131897 (2015)"},{"key":"4_CR29","unstructured":"Schulman, J., Moritz, P., et al.: High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438 (2015)"},{"key":"4_CR30","unstructured":"Schulman, J., Wolski, F., et al.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"4_CR31","unstructured":"Sunehag, P., Lever, G., et al.: Value-decomposition networks for cooperative multi-agent learning based on team reward. In: AAMAS, pp. 2085\u20132087 (2018)"},{"key":"4_CR32","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MuJoCo: a physics engine for model-based control. In: 2012 IROS, pp. 5026\u20135033 (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"4_CR34","unstructured":"Troost, S., Schuitema, E., Jonker, P.: Using cooperative multi-agent Q-learning to achieve action space decomposition within single robots. In: 1st ERLARS, p. 23 (2008)"},{"key":"4_CR35","unstructured":"Vaswani, A., Shazeer, N., et al.: Attention is all you need. In: NIPS, pp. 5998\u20136008 (2017)"},{"key":"4_CR36","unstructured":"Wang, T., Liao, R., et al.: NerveNet: learning structured policy with graph neural networks (2018)"},{"issue":"3\u20134","key":"4_CR37","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3\u20134), 229\u2013256 (1992). https:\/\/doi.org\/10.1007\/BF00992696","journal-title":"Mach. Learn."},{"key":"4_CR38","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/978-3-319-97304-3_15","volume-title":"PRICAI 2018: Trends in Artificial Intelligence","author":"C Yu","year":"2018","unstructured":"Yu, C., Wang, D., Ren, J., Ge, H., Sun, L.: Decentralized multiagent reinforcement learning for efficient robotic control by coordination graphs. In: Geng, X., Kang, B.-H. (eds.) PRICAI 2018. LNCS (LNAI), vol. 11012, pp. 191\u2013203. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-97304-3_15"}],"container-title":["Lecture Notes in Computer Science","Distributed Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-64096-5_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T17:27:14Z","timestamp":1669742834000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-64096-5_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030640958","9783030640965"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-64096-5_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"25 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Distributed Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dai22020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.adai.ai\/dai\/2020\/2020.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"22","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"9","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"41% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.77","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1.4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to the Corona pandemic this event was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}