{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T10:08:41Z","timestamp":1760609321688,"version":"3.37.3"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2021,2,13]],"date-time":"2021-02-13T00:00:00Z","timestamp":1613174400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,2,13]],"date-time":"2021-02-13T00:00:00Z","timestamp":1613174400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976178"],"award-info":[{"award-number":["61976178"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076202"],"award-info":[{"award-number":["62076202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Fuzzy Syst."],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1007\/s40815-020-01035-0","type":"journal-article","created":{"date-parts":[[2021,2,14]],"date-time":"2021-02-14T13:47:08Z","timestamp":1613310428000},"page":"1222-1233","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["A Fuzzy Curiosity-Driven Mechanism for Multi-Agent Reinforcement Learning"],"prefix":"10.1007","volume":"23","author":[{"given":"Wenbai","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haobin","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingchen","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kao-Shing","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,13]]},"reference":[{"key":"1035_CR1","doi-asserted-by":"crossref","unstructured":"de\u00a0Abril, I.M., Kanai, R.: Curiosity-driven reinforcement learning with homeostatic regulation. In: 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20136. IEEE (2018)","DOI":"10.1109\/IJCNN.2018.8489075"},{"key":"1035_CR2","doi-asserted-by":"crossref","unstructured":"Bu\u015foniu, L., Babu\u0161ka, R., De\u00a0Schutter, B.: Multi-agent reinforcement learning: An overview. In: Innovations in multi-agent systems and applications-1, pp. 183\u2013221. Springer (2010)","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"1035_CR3","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1613\/jair.1.11396","volume":"64","author":"FL Da Silva","year":"2019","unstructured":"Da Silva, F.L., Costa, A.H.R.: A survey on transfer learning for multiagent reinforcement learning systems. J. Artif. Intell. Res. 64, 645\u2013703 (2019)","journal-title":"J. Artif. Intell. Res."},{"key":"1035_CR4","unstructured":"Das, A., Gervet, T., Romoff, J., Batra, D., Parikh, D., Rabbat, M., Pineau, J.: Tarmac: Targeted multi-agent communication. In: International Conference on Machine Learning, pp. 1538\u20131546 (2019)"},{"key":"1035_CR5","doi-asserted-by":"publisher","first-page":"25","DOI":"10.3389\/fnbot.2013.00025","volume":"7","author":"M Frank","year":"2014","unstructured":"Frank, M., Leitner, J., Stollenga, M., F\u00f6rster, A., Schmidhuber, J.: Curiosity driven reinforcement learning for motion planning on humanoids. Front. Neurorobot 7, 25 (2014)","journal-title":"Front. Neurorobot"},{"key":"1035_CR6","unstructured":"Gupta, A., Mendonca, R., Liu, Y., Abbeel, P., Levine, S.: Meta-reinforcement learning of structured exploration strategies. In: Advances in Neural Information Processing Systems, pp. 5302\u20135311 (2018)"},{"key":"1035_CR7","doi-asserted-by":"crossref","unstructured":"Gupta, J.K., Egorov, M., Kochenderfer, M.: Cooperative multi-agent control using deep reinforcement learning. In: International Conference on Autonomous Agents and Multiagent Systems, pp. 66\u201383. Springer (2017)","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"1035_CR8","doi-asserted-by":"crossref","unstructured":"Hou, Y., Liu, L., Wei, Q., Xu, X., Chen, C.: A novel ddpg method with prioritized experience replay. In: 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 316\u2013321. IEEE (2017)","DOI":"10.1109\/SMC.2017.8122622"},{"key":"1035_CR9","doi-asserted-by":"crossref","unstructured":"Hsu, C.C., Hwang, H.T., Wu, Y.C., Tsao, Y., Wang, H.M.: Voice conversion from non-parallel corpora using variational auto-encoder. In: 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), pp. 1\u20136. IEEE (2016)","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"1035_CR10","unstructured":"Ibarz, B., Leike, J., Pohlen, T., Irving, G., Legg, S., Amodei, D.: Reward learning from human preferences and demonstrations in atari. In: Advances in neural information processing systems, pp. 8011\u20138023 (2018)"},{"key":"1035_CR11","unstructured":"Iqbal, S., Sha, F.: Actor-attention-critic for multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 2961\u20132970 (2019)"},{"key":"1035_CR12","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, W., Hu, Y., Hao, J., Chen, X., Gao, Y.: Multi-agent game abstraction via graph attention neural network. In: AAAI, pp. 7211\u20137218 (2020)","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"1035_CR13","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Abbeel, O.P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in neural information processing systems, pp. 6379\u20136390 (2017)"},{"key":"1035_CR14","doi-asserted-by":"crossref","unstructured":"Luo, Y., Huang, Z., Zhang, Z., Wang, Z., Li, J., Yang, Y.: Curiosity-driven reinforcement learning for diverse visual paragraph generation. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 2341\u20132350 (2019)","DOI":"10.1145\/3343031.3350961"},{"issue":"6","key":"1035_CR15","doi-asserted-by":"publisher","first-page":"4956","DOI":"10.1109\/TIE.2017.2674625","volume":"64","author":"J Ma","year":"2017","unstructured":"Ma, J., Zheng, Y., Wang, L.: Nash equilibrium topology of multi-agent systems with competitive groups. IEEE Trans. Ind. Electron. 64(6), 4956\u20134966 (2017)","journal-title":"IEEE Trans. Ind. Electron."},{"key":"1035_CR16","unstructured":"Mahajan, A., Rashid, T., Samvelyan, M., Whiteson, S.: Maven: Multi-agent variational exploration. In: Advances in Neural Information Processing Systems, pp. 7613\u20137624 (2019)"},{"key":"1035_CR17","doi-asserted-by":"crossref","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., et\u00a0al.: Human-level control through deep reinforcement learning. nature 518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"issue":"9","key":"1035_CR18","doi-asserted-by":"publisher","first-page":"2684","DOI":"10.1109\/TNNLS.2018.2885530","volume":"30","author":"Z Ni","year":"2019","unstructured":"Ni, Z., Paul, S.: A multistage game in smart grid security: A reinforcement learning solution. IEEE Trans. Neural Netw. Learn. Syst. 30(9), 2684\u20132695 (2019)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"1035_CR19","doi-asserted-by":"crossref","unstructured":"Now\u00e9, A., Vrancx, P., De\u00a0Hauwere, Y.M.: Game theory and multi-agent reinforcement learning. In: Reinforcement Learning, pp. 441\u2013470. Springer (2012)","DOI":"10.1007\/978-3-642-27645-3_14"},{"key":"1035_CR20","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 16\u201317 (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"1035_CR21","unstructured":"Rashid, T., Samvelyan, M., Schroeder, C., Farquhar, G., Foerster, J., Whiteson, S.: Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 4295\u20134304 (2018)"},{"issue":"1","key":"1035_CR22","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1109\/TII.2016.2617464","volume":"14","author":"H Shi","year":"2016","unstructured":"Shi, H., Li, X., Hwang, K.S., Pan, W., Xu, G.: Decoupled visual servoing with fuzzy q-learning. IEEE Trans. Ind. Inform. 14(1), 241\u2013252 (2016)","journal-title":"IEEE Trans. Ind. Inform."},{"key":"1035_CR23","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1016\/j.ins.2018.01.032","volume":"436","author":"H Shi","year":"2018","unstructured":"Shi, H., Lin, Z., Zhang, S., Li, X., Hwang, K.S.: An adaptive decision-making method with fuzzy bayesian reinforcement learning for robot soccer. Inf. Sci. 436, 268\u2013281 (2018)","journal-title":"Inf. Sci."},{"issue":"4","key":"1035_CR24","doi-asserted-by":"publisher","first-page":"2393","DOI":"10.1109\/TII.2019.2936167","volume":"16","author":"H Shi","year":"2019","unstructured":"Shi, H., Shi, L., Xu, M., Hwang, K.S.: End-to-end navigation strategy with deep reinforcement learning for mobile robots. IEEE Trans. Ind. Inform. 16(4), 2393\u20132402 (2019)","journal-title":"IEEE Trans. Ind. Inform."},{"issue":"7","key":"1035_CR25","doi-asserted-by":"publisher","first-page":"1936","DOI":"10.1109\/TAC.2013.2294621","volume":"59","author":"ME Valcher","year":"2013","unstructured":"Valcher, M.E., Misra, P.: On the stabilizability and consensus of positive homogeneous multi-agent dynamical systems. IEEE Trans. Autom. Control 59(7), 1936\u20131941 (2013)","journal-title":"IEEE Trans. Autom. Control"},{"key":"1035_CR26","unstructured":"Yang, Y., Luo, R., Li, M., Zhou, M., Zhang, W., Wang, J.: Mean field multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 5571\u20135580 (2018)"},{"issue":"16","key":"1035_CR27","doi-asserted-by":"publisher","first-page":"1881","DOI":"10.1049\/iet-cta.2011.0033","volume":"5","author":"Y Zheng","year":"2011","unstructured":"Zheng, Y., Zhu, Y., Wang, L.: Consensus of heterogeneous multi-agent systems. IET Control Theory Appl. 5(16), 1881\u20131888 (2011)","journal-title":"IET Control Theory Appl."}],"container-title":["International Journal of Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40815-020-01035-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40815-020-01035-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40815-020-01035-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T09:26:34Z","timestamp":1671269194000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40815-020-01035-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,13]]},"references-count":27,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["1035"],"URL":"https:\/\/doi.org\/10.1007\/s40815-020-01035-0","relation":{},"ISSN":["1562-2479","2199-3211"],"issn-type":[{"type":"print","value":"1562-2479"},{"type":"electronic","value":"2199-3211"}],"subject":[],"published":{"date-parts":[[2021,2,13]]},"assertion":[{"value":"4 August 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 December 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 December 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 February 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}