{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T16:11:08Z","timestamp":1776355868981,"version":"3.51.2"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,5,13]],"date-time":"2023-05-13T00:00:00Z","timestamp":1683936000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,13]],"date-time":"2023-05-13T00:00:00Z","timestamp":1683936000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61903109"],"award-info":[{"award-number":["61903109"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Vis"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s12650-023-00928-0","type":"journal-article","created":{"date-parts":[[2023,5,13]],"date-time":"2023-05-13T09:02:38Z","timestamp":1683968558000},"page":"1189-1205","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["MADDPGViz: a visual analytics approach to understand multi-agent deep reinforcement learning"],"prefix":"10.1007","volume":"26","author":[{"given":"Xiaoying","family":"Shi","sequence":"first","affiliation":[]},{"given":"Jiaming","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Ziyi","family":"Liang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0921-848X","authenticated-orcid":false,"given":"Dewen","family":"Seng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,5,13]]},"reference":[{"issue":"01","key":"928_CR1","first-page":"4561","volume":"33","author":"RM Annasamy","year":"2019","unstructured":"Annasamy RM, Sycara K (2019) Towards better interpretability in deep q-networks. Proc AAAI Conf Artif Intell 33(01):4561\u20134569","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"928_CR2","unstructured":"Bellemare M G, Dabney W, Munos R (2017) A distributional perspective on reinforcement learning. In: Proceedings of international conference on machine learning 449\u2013458"},{"key":"928_CR3","doi-asserted-by":"crossref","unstructured":"Chen W, Zhou K, Chen C (2016) Real-time bus holding control on a transit corridor based on multi-agent reinforcement learning. In: Proceedings of 2016 IEEE 19th international conference on intelligent transportation systems (ITSC) 100\u2013106.","DOI":"10.1109\/ITSC.2016.7795538"},{"key":"928_CR4","doi-asserted-by":"crossref","unstructured":"Chen J, Yuan B, Tomizuka M (2019) Model-free deep reinforcement learning for urban autonomous driving. In: Proceedings of 2019 IEEE intelligent transportation systems conference (ITSC) 2765\u20132771.","DOI":"10.1109\/ITSC.2019.8917306"},{"issue":"3","key":"928_CR5","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1109\/TITS.2019.2901791","volume":"21","author":"T Chu","year":"2019","unstructured":"Chu T, Wang J, Codec\u00e0 L et al (2019) Multi-agent deep reinforcement learning for large-scale traffic signal control. IEEE Trans Intell Transp Syst 21(3):1086\u20131095","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"928_CR6","doi-asserted-by":"crossref","unstructured":"Du W, Ding S (2020) A survey on multi-agent deep reinforcement learning: from the perspective of challenges and applications. Artif Intell Rev 1\u201324","DOI":"10.1007\/s10462-020-09938-y"},{"key":"928_CR7","unstructured":"Foerster J, Nardelli N, Farquhar G, et al (2017) Stabilising experience replay for deep multi-agent reinforcement learning. In: Proceedings of international conference on machine learning 1146\u20131155"},{"key":"928_CR8","doi-asserted-by":"crossref","unstructured":"Foerster J, Farquhar G, Afouras T, et al (2018) Counterfactual multi-agent policy gradients. In: Proceedings of the AAAI conference on artificial intelligence 32(1).","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"928_CR9","unstructured":"Greydanus S, Koul A, Dodge J, et al (2018) Visualizing and understanding atari agents. In: Proceedings of international conference on machine learning 1792\u20131801"},{"key":"928_CR10","doi-asserted-by":"crossref","unstructured":"Gu S, Holly E, Lillicrap T, et al (2017) Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In: Proceedings of 2017 IEEE international conference on robotics and automation (ICRA) 3389\u20133396","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"928_CR11","doi-asserted-by":"crossref","unstructured":"Gupta J K, Egorov M, Kochenderfer M (2017) Cooperative multi-agent control using deep reinforcement learning. In: Proceedings of international conference on autonomous agents and multiagent systems 66\u201383.","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"928_CR12","unstructured":"Haarnoja T, Zhou A, Abbeel P, et al (2018) Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: Proceedings of international conference on machine learning 1861\u20131870"},{"key":"928_CR14","doi-asserted-by":"crossref","unstructured":"He W, Lee T Y, van Baar J, et al (2020) DynamicsExplorer: visual analytics for robot control tasks involving dynamics and LSTM-based control policies. In: Proceedings of 2020 IEEE pacific visualization symposium (PacificVis) 36\u201345","DOI":"10.1109\/PacificVis48177.2020.7127"},{"key":"928_CR15","doi-asserted-by":"crossref","unstructured":"Hessel M, Modayil J, Van Hasselt H, et al (2018) Rainbow: combining improvements in deep reinforcement learning. In: Proceedings of the AAAI conference on artificial intelligence 32(1).","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"928_CR16","unstructured":"Iqbal S, Sha F (2019) Actor-attention-critic for multi-agent reinforcement learning. In: Proceedings of international conference on machine learning 2961\u20132970"},{"issue":"3","key":"928_CR17","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1111\/cgf.13962","volume":"39","author":"T Jaunet","year":"2020","unstructured":"Jaunet T, Vuillemot R, Wolf C (2020) DRLViz: Understanding decisions and memory in deep reinforcement learning. Comput Gr Forum 39(3):49\u201361","journal-title":"Comput Gr Forum"},{"key":"928_CR18","doi-asserted-by":"crossref","unstructured":"Kindermans P J, Hooker S, Adebayo J, et al (2019) The (un) reliability of saliency methods. Explainable AI: Interpreting, Explaining and Visualizing Deep Learning 267\u2013280","DOI":"10.1007\/978-3-030-28954-6_14"},{"key":"928_CR19","doi-asserted-by":"crossref","unstructured":"Kurek M, Ja\u015bkowski W (2016) Heterogeneous team deep q-learning in low-dimensional multi-agent environment. In: Proceedings of 2016 IEEE conference on computational intelligence and games (CIG) 1\u20138.","DOI":"10.1109\/CIG.2016.7860413"},{"issue":"01","key":"928_CR20","first-page":"4213","volume":"33","author":"S Li","year":"2019","unstructured":"Li S, Wu Y, Cui X et al (2019) Robust multi-agent reinforcement learning via minimax deep deterministic policy gradient. Proc AAAI Conf Artif Intel 33(01):4213\u20134220","journal-title":"Proc AAAI Conf Artif Intel"},{"key":"928_CR21","unstructured":"Lillicrap T P, Hunt J J, Pritzel A, et al (2016) Continuous control with deep reinforcement learning. In: Proceedings of the 4th international conference on learning representations 1\u201310"},{"issue":"12","key":"928_CR22","doi-asserted-by":"publisher","first-page":"2436","DOI":"10.1109\/TVCG.2013.196","volume":"19","author":"S Liu","year":"2013","unstructured":"Liu S, Wu Y, Wei E et al (2013) Storyflow: tracking the evolution of stories. IEEE Trans Vis Comput Gr 19(12):2436\u20132445","journal-title":"IEEE Trans Vis Comput Gr"},{"key":"928_CR23","unstructured":"Lowe R, Wu Y I, Tamar A, et al (2017) Multi-agent actor-critic for mixed cooperative-competitive environments. In: Proceedings of advances in neural information processing systems 6379\u20136390."},{"issue":"7540","key":"928_CR25","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"key":"928_CR26","unstructured":"Mnih V, Badia A P, Mirza M, et al (2016) Asynchronous methods for deep reinforcement learning. In: Proceedings of international conference on machine learning 1928\u20131937"},{"key":"928_CR27","doi-asserted-by":"crossref","unstructured":"Mordatch I, Abbeel P (2018) Emergence of grounded compositional language in multi-agent populations. In: Proceedings of the AAAI conference on artificial intelligence 32(1)","DOI":"10.1609\/aaai.v32i1.11492"},{"key":"928_CR28","unstructured":"Parisotto E, Salakhutdinov R (2018) Neural map: Structured memory for deep reinforcement learning. In: Proceedings of the 6th international conference on learning representations 1\u201313"},{"key":"928_CR29","doi-asserted-by":"crossref","unstructured":"Poli\u010dar P G, Stra\u017ear M, Zupan B (2019) openTSNE: a modular Python library for t-SNE dimensionality reduction and embedding. BioRxiv 731877.","DOI":"10.1101\/731877"},{"issue":"05","key":"928_CR30","first-page":"7236","volume":"34","author":"H Ryu","year":"2020","unstructured":"Ryu H, Shin H, Park J (2020) Multi-agent actor-critic with hierarchical graph attention network. Proc AAAI Conf Artif Intell 34(05):7236\u20137243","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"928_CR31","unstructured":"Schulman J, Wolski F, Dhariwal P, et al (2017) Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347."},{"key":"928_CR32","unstructured":"Such F P, Madhavan V, Liu R, et al (2019) An atari model zoo for analyzing, visualizing, and comparing deep reinforcement learning agents. In: Proceedings of the 28th international joint conference on artificial intelligence 3260\u20133267"},{"issue":"4","key":"928_CR33","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395","volume":"12","author":"A Tampuu","year":"2017","unstructured":"Tampuu A, Matiisen T, Kodelja D et al (2017) Multiagent cooperation and competition with deep reinforcement learning. PLoS ONE 12(4):e0172395","journal-title":"PLoS ONE"},{"key":"928_CR24","unstructured":"Van der Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9(11)"},{"key":"928_CR13","doi-asserted-by":"crossref","unstructured":"Van Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI conference on artificial intelligence 30(1)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"928_CR34","unstructured":"Wai H T, Yang Z, Wang Z, et al (2018) Multi-agent reinforcement learning via double averaging primal-dual optimization. In: Proceedings of the 32nd international conference on neural information processing systems 9672\u20139683"},{"issue":"1","key":"928_CR35","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1109\/TVCG.2018.2864504","volume":"25","author":"J Wang","year":"2018","unstructured":"Wang J, Gou L, Shen HW et al (2018) Dqnviz: a visual analytics approach to understand deep q-networks. IEEE Trans Visual Comput Graphics 25(1):288\u2013298","journal-title":"IEEE Trans Visual Comput Graphics"},{"key":"928_CR36","unstructured":"Wang Z, Schaul T, Hessel M, et al (2016) Dueling network architectures for deep reinforcement learning. In: Proceedings of international conference on machine learning 1995\u20132003"},{"key":"928_CR37","doi-asserted-by":"publisher","first-page":"1720","DOI":"10.1109\/TVCG.2020.3030432","volume":"27","author":"J Yuan","year":"2021","unstructured":"Yuan J, Xiang S, Xia J et al (2021) Evaluation of Sampling Methods for Scatterplots. IEEE Trans Visual Comput Graphics 27:1720\u20131730","journal-title":"IEEE Trans Visual Comput Graphics"},{"key":"928_CR38","unstructured":"Zahavy T, Ben-Zrihem N, Mannor S (2016) Graying the black box: Understanding dqns. In: Proceedings of international conference on machine learning 1899\u20131908"}],"container-title":["Journal of Visualization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12650-023-00928-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12650-023-00928-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12650-023-00928-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T05:21:01Z","timestamp":1692681661000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12650-023-00928-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,13]]},"references-count":38,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["928"],"URL":"https:\/\/doi.org\/10.1007\/s12650-023-00928-0","relation":{},"ISSN":["1343-8875","1875-8975"],"issn-type":[{"value":"1343-8875","type":"print"},{"value":"1875-8975","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,13]]},"assertion":[{"value":"23 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 September 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 April 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}