{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T06:07:40Z","timestamp":1743055660867,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030845285"},{"type":"electronic","value":"9783030845292"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-84529-2_56","type":"book-chapter","created":{"date-parts":[[2021,8,9]],"date-time":"2021-08-09T15:01:42Z","timestamp":1628521302000},"page":"665-680","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Accelerating Deep Reinforcement Learning via Hierarchical State Encoding with ELMs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5173-1191","authenticated-orcid":false,"given":"Tao","family":"Tang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5063-6889","authenticated-orcid":false,"given":"Qiang","family":"Fang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3238-745X","authenticated-orcid":false,"given":"Xin","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5765-684X","authenticated-orcid":false,"given":"Yujun","family":"Zeng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,8,9]]},"reference":[{"issue":"7839","key":"56_CR1","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/s41586-020-03051-4","volume":"588","author":"J Schrittwieser","year":"2020","unstructured":"Schrittwieser, J., Antonoglou, I., Hubert, T.: Mastering Atari, Go, chess and shogi by planning with a learned model. Nature 588(7839), 604\u2013609 (2020)","journal-title":"Nature"},{"issue":"7540","key":"56_CR2","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.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"issue":"3","key":"56_CR3","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1038\/s42256-019-0025-4","volume":"1","author":"EO Neftci","year":"2019","unstructured":"Neftci, E.O., Averbeck, B.: Reinforcement learning in artificial and biological systems. Nat. Mach. Intell. 1(3), 133\u2013143 (2019)","journal-title":"Nat. Mach. Intell."},{"issue":"7587","key":"56_CR4","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"issue":"7782","key":"56_CR5","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., Babuschkin, I., Czarnecki, W.M.: Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","journal-title":"Nature"},{"key":"56_CR6","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D.: Playing Atari with deep reinforcement learning. Computer Science (2013)"},{"issue":"19","key":"56_CR7","doi-asserted-by":"publisher","first-page":"70","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023","volume":"2017","author":"AEL Sallab","year":"2017","unstructured":"Sallab, A.E.L., Abdou, M., Perot, E.: Deep reinforcement learning framework for autonomous driving. Electron. Imaging 2017(19), 70\u201376 (2017)","journal-title":"Electron. Imaging"},{"key":"56_CR8","doi-asserted-by":"crossref","unstructured":"Gu, S., Holly, E., Lillicrap, T.: Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 3389\u20133396. IEEE, Singapore (2017)","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"56_CR9","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MuJoCo: a physics engine for model-based control. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, Portugal, pp. 5026\u20135033. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"56_CR10","unstructured":"Tassa, Y., Doron, Y.: Deepmind control suite. arXiv preprint arXiv:1801.00690 (2018)"},{"key":"56_CR11","doi-asserted-by":"crossref","unstructured":"Lange, S., Riedmiller, M.: Deep auto-encoder neural networks in reinforcement learning. In: International Joint Conference on Neural Networks, Spain, pp. 1\u20138. IEEE (2010)","DOI":"10.1109\/IJCNN.2010.5596468"},{"key":"56_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1007\/978-3-642-34500-5_16","volume-title":"Neural Information Processing","author":"J Mattner","year":"2012","unstructured":"Mattner, J., Lange, S., Riedmiller, M.: Learn to swing up and balance a real pole based on raw visual input data. In: Huang, T., Zeng, Z., Li, C., Leung, C.S. (eds.) ICONIP 2012. LNCS, vol. 7667, pp. 126\u2013133. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-34500-5_16"},{"key":"56_CR13","doi-asserted-by":"crossref","unstructured":"Dwibedi, D., Tompson, J., Lynch, C.: Learning actionable representations from visual observations. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1577\u20131584. IEEE (2019)","DOI":"10.1109\/IROS.2018.8593951"},{"key":"56_CR14","unstructured":"Srinivas, A., Laskin, M., Abbeel, P.: CURL: contrastive unsupervised representations for reinforcement learning. arXiv e-prints arXiv:2004.04136 (2020)"},{"key":"56_CR15","unstructured":"Ha, D., Schmidhuber, J.: Recurrent world models facilitate policy evolution. arXiv e-prints arXiv:1809.01999 (2018)"},{"key":"56_CR16","unstructured":"Lee, A.X., Nagabandi, A., Abbeel, P.: Stochastic latent actor-critic: deep reinforcement learning with a latent variable model. arXiv e-prints arXiv:1907.00953 (2019)"},{"issue":"1\u20133","key":"56_CR17","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.neucom.2005.12.126","volume":"70","author":"GB Huang","year":"2006","unstructured":"Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: theory and applications. Neurocomputing 70(1\u20133), 489\u2013501 (2006)","journal-title":"Neurocomputing"},{"key":"56_CR18","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1115\/1.3426922","volume":"97","author":"JS Albus","year":"1975","unstructured":"Albus, J.S.: A new approach to manipulator control: the Cerebellar Model Articulation Controller (CMAC). Trans. ASME J. Dyn. Syst. 97, 220\u2013227 (1975)","journal-title":"Trans. ASME J. Dyn. Syst."},{"key":"56_CR19","unstructured":"Schulman, J., Wolski, F., Dhariwal, P.: Proximal policy optimization algorithms. arXiv e-prints arXiv:1707.06347 (2017)"},{"key":"56_CR20","unstructured":"Lillicrap, T.P., Hunt, J., Pritzel, A.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971(2015)"},{"key":"56_CR21","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"56_CR22","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1613\/jair.946","volume":"16","author":"X Xu","year":"2002","unstructured":"Xu, X., He, H., Hu, D.: Efficient reinforcement learning using recursive least-squares methods. J. Artif. Intell. Res. 16, 259\u2013292 (2002)","journal-title":"J. Artif. Intell. Res."}],"container-title":["Lecture Notes in Computer Science","Intelligent Computing Theories and Application"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-84529-2_56","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:10:54Z","timestamp":1710256254000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-84529-2_56"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030845285","9783030845292"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-84529-2_56","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"9 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 August 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 August 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2021a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2021\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}