{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T07:42:01Z","timestamp":1675150921392},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T00:00:00Z","timestamp":1669680000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T00:00:00Z","timestamp":1669680000000},"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":["Artif Life Robotics"],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1007\/s10015-022-00833-z","type":"journal-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T09:04:22Z","timestamp":1669712662000},"page":"67-75","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Generating collective wall-jumping behavior for a robotic swarm with self-teaching automatic curriculum learning"],"prefix":"10.1007","volume":"28","author":[{"given":"Xiaotong","family":"Nie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yupeng","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyao","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhiro","family":"Ohkura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,29]]},"reference":[{"key":"833_CR1","doi-asserted-by":"crossref","unstructured":"\u015eahin E (2004) Swarm robotics: from sources of inspiration to domains of application. In: International workshop on swarm robotics. Springer, pp 10\u201320","DOI":"10.1007\/978-3-540-30552-1_2"},{"issue":"4","key":"833_CR2","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1007\/BF00175101","volume":"28","author":"TD Seeley","year":"1991","unstructured":"Seeley TD, Camazine S, Sneyd J (1991) Collective decision-making in honey bees: how colonies choose among nectar sources. Behav Ecol Sociobiol 28(4):277\u2013290","journal-title":"Behav Ecol Sociobiol"},{"key":"833_CR3","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1016\/j.neucom.2015.05.116","volume":"172","author":"L Bay\u0131nd\u0131r","year":"2016","unstructured":"Bay\u0131nd\u0131r L (2016) A review of swarm robotics tasks. Neurocomputing 172:292\u2013321","journal-title":"Neurocomputing"},{"key":"833_CR4","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/978-3-642-33093-3_38","volume-title":"From animals to animats 12","author":"G Francesca","year":"2012","unstructured":"Francesca G, Brambilla M, Trianni V, Dorigo M, Birattari M (2012) Analysing an evolved robotic behaviour using a biological model of collegial decision making. In: Ziemke T, Balkenius C, Hallam J (eds) From animals to animats 12. Springer Berlin Heidelberg, Berlin, Heidelberg, pp 381\u2013390"},{"key":"833_CR5","doi-asserted-by":"publisher","first-page":"01","DOI":"10.1504\/IJBIC.2009.022770","volume":"1","author":"R Gro\u00df","year":"2009","unstructured":"Gro\u00df R, Dorigo M (2009) Towards group transport by swarms of robots. Int J Bio-Inspir Comput 1:01","journal-title":"Int J Bio-Inspir Comput"},{"issue":"5","key":"833_CR6","doi-asserted-by":"publisher","first-page":"621","DOI":"10.20965\/jaciii.2018.p0621","volume":"22","author":"M Hiraga","year":"2018","unstructured":"Hiraga M, Yasuda T, Ohkura K (2018) Evolutionary acquisition of autonomous specialization in a path-formation task of a robotic swarm. J Adv Comput Intell Intell Inform 22(5):621\u2013628","journal-title":"J Adv Comput Intell Intell Inform"},{"key":"833_CR7","doi-asserted-by":"crossref","unstructured":"Gu S, Holly E, Lillicrap T, Levine S (2017) Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In: 2017 IEEE international conference on robotics and automation (ICRA), pp 3389\u20133396. IEEE","DOI":"10.1109\/ICRA.2017.7989385"},{"issue":"11","key":"833_CR8","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1177\/0278364913495721","volume":"32","author":"J Kober","year":"2013","unstructured":"Kober J, Bagnell JA, Peters J (2013) Reinforcement learning in robotics: a survey. Int J Rob Res 32(11):1238\u20131274","journal-title":"Int J Rob Res"},{"issue":"54","key":"833_CR9","first-page":"1","volume":"20","author":"M H\u00fcttenrauch","year":"2019","unstructured":"H\u00fcttenrauch M, Adrian S, Neumann G et al (2019) Deep reinforcement learning for swarm systems. J Mach Learn Res 20(54):1\u201331","journal-title":"J Mach Learn Res"},{"key":"833_CR10","doi-asserted-by":"crossref","unstructured":"Bengio Y, Louradour J, Collobert R, Weston J (2009) Curriculum learning. In: Proceedings of the 26th annual international conference on machine learning, pp 41\u201348","DOI":"10.1145\/1553374.1553380"},{"key":"833_CR11","first-page":"4555","volume":"44","author":"X Wang","year":"2021","unstructured":"Wang X, Chen Y, Zhu W (2021) A survey on curriculum learning. IEEE Trans Pattern Anal Mach Intell 44:4555\u20134576","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"833_CR12","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1016\/S1672-6529(14)60133-5","volume":"12","author":"D Chen","year":"2015","unstructured":"Chen D, Chen K, Zhang Z, Zhang B (2015) Mechanism of locust air posture adjustment. J Bionic Eng 12(3):418\u2013431","journal-title":"J Bionic Eng"},{"issue":"5","key":"833_CR13","doi-asserted-by":"publisher","first-page":"1007","DOI":"10.1109\/TRO.2012.2198510","volume":"28","author":"M Noh","year":"2012","unstructured":"Noh M, Kim S-W, An S, Koh J-S, Cho K-J (2012) Flea-inspired catapult mechanism for miniature jumping robots. IEEE Trans Rob 28(5):1007\u20131018","journal-title":"IEEE Trans Rob"},{"key":"833_CR14","doi-asserted-by":"crossref","unstructured":"Romanishin JW, Gilpin K, Rus D (2013) M-blocks: momentum-driven, magnetic modular robots. In: 2013 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp 4288\u20134295. IEEE","DOI":"10.1109\/IROS.2013.6696971"},{"issue":"7540","key":"833_CR15","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, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"key":"833_CR16","unstructured":"Kulkarni TD, Narasimhan K, Saeedi A, Tenenbaum J (2016) Hierarchical deep reinforcement learning: integrating temporal abstraction and intrinsic motivation. Adv Neural Inform Process Syst 29"},{"key":"833_CR17","unstructured":"Duan Y, Chen X, Houthooft R, Schulman J, Abbeel P (2016) Benchmarking deep reinforcement learning for continuous control. In: International conference on machine learning, pp 1329\u20131338. PMLR"},{"key":"833_CR18","unstructured":"Matiisen T, Oliver A, Cohen T, Schulman J (2017) Teacher-student curriculum learning"},{"key":"833_CR19","doi-asserted-by":"crossref","unstructured":"Portelas R, Colas C, Weng L, Hofmann K, Oudeyer P-Y (2020) Automatic curriculum learning for deep RL: a short survey. CoRR, abs\/2003.04664","DOI":"10.24963\/ijcai.2020\/671"},{"key":"833_CR20","doi-asserted-by":"crossref","unstructured":"Ivanovic B, Harrison J, Sharma A, Chen M, Pavone M (2018) Backward reachability curriculum for robotic reinforcement learning, Barc","DOI":"10.1109\/ICRA.2019.8794206"},{"key":"833_CR21","unstructured":"Salimans T, Chen R (2018) Learning Montezuma\u2019s revenge from a single demonstration. CoRR"},{"key":"833_CR22","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347"}],"container-title":["Artificial Life and Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10015-022-00833-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10015-022-00833-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10015-022-00833-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T07:19:12Z","timestamp":1675149552000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10015-022-00833-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,29]]},"references-count":22,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,2]]}},"alternative-id":["833"],"URL":"https:\/\/doi.org\/10.1007\/s10015-022-00833-z","relation":{},"ISSN":["1433-5298","1614-7456"],"issn-type":[{"value":"1433-5298","type":"print"},{"value":"1614-7456","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,29]]},"assertion":[{"value":"10 June 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 November 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}