{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T13:01:39Z","timestamp":1743080499781,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819789627"},{"type":"electronic","value":"9789819789634"}],"license":[{"start":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T00:00:00Z","timestamp":1735084800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T00:00:00Z","timestamp":1735084800000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-8963-4_5","type":"book-chapter","created":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T22:59:45Z","timestamp":1735081185000},"page":"41-52","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Memory-Augmented Deep Deterministic Policy Gradient"],"prefix":"10.1007","author":[{"given":"Qian","family":"Qiu","sequence":"first","affiliation":[]},{"given":"Fanyu","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Haigen","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Guanyu","family":"Xing","sequence":"additional","affiliation":[]},{"given":"Shuzhi Sam","family":"Ge","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,25]]},"reference":[{"issue":"6","key":"5_CR1","doi-asserted-by":"publisher","first-page":"899","DOI":"10.1109\/JIOT.2016.2612119","volume":"3","author":"NH Motlagh","year":"2016","unstructured":"Motlagh, N.H., Taleb, T., Arouk, O.: Low-altitude unmanned aerial vehicles-based internet of things services: comprehensive survey and future perspectives. IEEE Internet Things J. 3(6), 899\u2013922 (2016)","journal-title":"IEEE Internet Things J."},{"issue":"6","key":"5_CR2","doi-asserted-by":"publisher","first-page":"3747","DOI":"10.1109\/TWC.2017.2688328","volume":"16","author":"Y Zeng","year":"2017","unstructured":"Zeng, Y., Zhang, R.: Energy-efficient UAV communication with trajectory optimization. IEEE Trans. Wireless Commun. 16(6), 3747\u20133760 (2017)","journal-title":"IEEE Trans. Wireless Commun."},{"issue":"1","key":"5_CR3","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1016\/j.ast.2013.04.005","volume":"29","author":"SG Kontogiannis","year":"2013","unstructured":"Kontogiannis, S.G., Ekaterinaris, J.A.: Design, performance evaluation and optimization of a UAV. Aerosp. Sci. Technol. 29(1), 339\u2013350 (2013)","journal-title":"Aerosp. Sci. Technol."},{"issue":"3","key":"5_CR4","doi-asserted-by":"publisher","first-page":"2109","DOI":"10.1109\/TWC.2017.2789293","volume":"17","author":"Q Wu","year":"2018","unstructured":"Wu, Q., Zeng, Y., Zhang, R.: Joint trajectory and communication design for multi-UAV enabled wireless networks. IEEE Trans. Wireless Commun. 17(3), 2109\u20132121 (2018)","journal-title":"IEEE Trans. Wireless Commun."},{"issue":"7","key":"5_CR5","first-page":"1477","volume":"28","author":"F Xiao","year":"2019","unstructured":"Xiao, F.: EFMCDM: evidential fuzzy multicriteria decision making based on belief entropy. IEEE Trans. Fuzzy Syst. 28(7), 1477\u20131491 (2019)","journal-title":"IEEE Trans. Fuzzy Syst."},{"issue":"1","key":"5_CR6","doi-asserted-by":"publisher","first-page":"86","DOI":"10.21629\/JSEE.2018.01.09","volume":"29","author":"H Changqiang","year":"2018","unstructured":"Changqiang, H., Kangsheng, D., Hanqiao, H., et al.: Autonomous air combat maneuver decision using Bayesian inference and moving horizon optimisation. J. Syst. Eng. Electron. 29(1), 86\u201397 (2018)","journal-title":"J. Syst. Eng. Electron."},{"issue":"11","key":"5_CR7","first-page":"13953","volume":"72","author":"Y Hou","year":"2023","unstructured":"Hou, Y., Liang, X., Zhang, J., et al.: Hierarchical decision-making framework for multiple UCAVs autonomous confrontation. IEEE Trans. Veh. Technol. 72(11), 13953\u201313968 (2023)","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"3","key":"5_CR8","doi-asserted-by":"publisher","first-page":"2124","DOI":"10.1109\/TVT.2018.2890773","volume":"68","author":"C Wang","year":"2019","unstructured":"Wang, C., Wang, J., Shen, Y., et al.: Autonomous navigation of UAVs in large-scale complex environments: a deep reinforcement learning approach. IEEE Trans. Veh. Technol. 68(3), 2124\u20132136 (2019)","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"4","key":"5_CR9","doi-asserted-by":"publisher","first-page":"5064","DOI":"10.1109\/TNNLS.2022.3207346","volume":"35","author":"X Wang","year":"2022","unstructured":"Wang, X., Wang, S., Liang, X., et al.: Deep reinforcement learning: a survey. IEEE Trans. Neural Netw. Learn. Syst. 35(4), 5064\u20135078 (2022)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"5_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2021.107052","volume":"118","author":"L He","year":"2021","unstructured":"He, L., Aouf, N., Song, B.: Explainable Deep Reinforcement Learning for UAV autonomous path planning. Aerosp. Sci. Technol. 118, 107052 (2021)","journal-title":"Aerosp. Sci. Technol."},{"issue":"5","key":"5_CR11","doi-asserted-by":"publisher","first-page":"5723","DOI":"10.1109\/TVT.2020.2982508","volume":"69","author":"Q Liu","year":"2020","unstructured":"Liu, Q., Shi, L., Sun, L., et al.: Path planning for UAV-mounted mobile edge computing with deep reinforcement learning. IEEE Trans. Veh. Technol. 69(5), 5723\u20135728 (2020)","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"1","key":"5_CR12","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1109\/TSG.2019.2924025","volume":"11","author":"VH Bui","year":"2019","unstructured":"Bui, V.H., Hussain, A., Kim, H.M.: Double deep Q-learning-based distributed operation of battery energy storage system considering uncertainties. IEEE Trans. Smart Grid 11(1), 457\u2013469 (2019)","journal-title":"IEEE Trans. Smart Grid"},{"issue":"3","key":"5_CR13","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.1109\/TNSE.2022.3172794","volume":"10","author":"H Tang","year":"2022","unstructured":"Tang, H., Wu, H., Qu, G., et al.: Double deep Q-network based dynamic framing offloading in vehicular edge computing. IEEE Trans. Netw. Sci. Eng. 10(3), 1297\u20131310 (2022)","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"issue":"1","key":"5_CR14","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TNN.2009.2034145","volume":"21","author":"T Dierks","year":"2009","unstructured":"Dierks, T., Jagannathan, S.: Output feedback control of a quadrotor UAV using neural networks. IEEE Trans. Neural Networks 21(1), 50\u201366 (2009)","journal-title":"IEEE Trans. Neural Networks"},{"issue":"1","key":"5_CR15","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1109\/TG.2023.3236065","volume":"16","author":"Y Xue","year":"2023","unstructured":"Xue, Y., Sun, Y., Zhou, J., et al.: Multi-attribute decision-making in wargames leveraging the Entropy-Weight method in conjunction with deep reinforcement learning. IEEE Trans. Games 16(1), 151\u2013161 (2023)","journal-title":"IEEE Trans. Games"},{"issue":"4","key":"5_CR16","doi-asserted-by":"publisher","first-page":"804","DOI":"10.1109\/TSMCA.2005.855778","volume":"36","author":"VN Huynh","year":"2006","unstructured":"Huynh, V.N., Nakamori, Y., Ho, T.B., et al.: Multiple-attribute decision making under uncertainty: the evidential reasoning approach revisited. IEEE Trans. Syst. Man Cybern.-Part A Syst. Hum. 36(4), 804\u2013822 (2006)","journal-title":"IEEE Trans. Syst. Man Cybern.-Part A Syst. Hum."},{"unstructured":"Engstrom, L., Ilyas, A., Santurkar, S., et al.: Implementation matters in deep RL: a case study on PPO and TRPO. In: International Conference on Learning Representations (2019)","key":"5_CR17"},{"key":"5_CR18","first-page":"24611","volume":"35","author":"C Yu","year":"2022","unstructured":"Yu, C., Velu, A., Vinitsky, E., et al.: The surprising effectiveness of PPO in cooperative multi-agent games. Adv. Neural. Inf. Process. Syst. 35, 24611\u201324624 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"8","key":"5_CR19","first-page":"3772","volume":"29","author":"T Ergen","year":"2017","unstructured":"Ergen, T., Kozat, S.S.: Efficient online learning algorithms based on LSTM neural networks. IEEE Trans. Neural Netw. Learn. Syst. 29(8), 3772\u20133783 (2017)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"8","key":"5_CR20","first-page":"3600","volume":"69","author":"C Yang","year":"2022","unstructured":"Yang, C., Xia, Y., Chu, Z., et al.: Logic synthesis optimisation sequence tuning using RL-based LSTM and graph isomorphism network. IEEE Trans. Circuits Syst. II Express Briefs 69(8), 3600\u20133604 (2022)","journal-title":"IEEE Trans. Circuits Syst. II Express Briefs"}],"container-title":["Lecture Notes in Computer Science","Social Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8963-4_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T23:02:14Z","timestamp":1735081334000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8963-4_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,25]]},"ISBN":["9789819789627","9789819789634"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8963-4_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,25]]},"assertion":[{"value":"25 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICSR + BioMed","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Social Robotics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"socrob2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/robicon2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}