{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:58:05Z","timestamp":1740099485961,"version":"3.37.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030304867"},{"type":"electronic","value":"9783030304874"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-30487-4_47","type":"book-chapter","created":{"date-parts":[[2019,9,8]],"date-time":"2019-09-08T19:02:47Z","timestamp":1567969367000},"page":"611-623","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Mixed-Reality Deep Reinforcement Learning for a Reach-to-grasp Task"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8170-2471","authenticated-orcid":false,"given":"Hadi","family":"Beik Mohammadi","sequence":"first","affiliation":[]},{"given":"Mohammad Ali","family":"Zamani","sequence":"additional","affiliation":[]},{"given":"Matthias","family":"Kerzel","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,9,9]]},"reference":[{"key":"47_CR1","unstructured":"Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint \n                      arXiv:1603.04467\n                      \n                     (2016)"},{"key":"47_CR2","doi-asserted-by":"publisher","unstructured":"Beeson, P., Ames, B.: TRAC-IK: an open-source library for improved solving of generic inverse kinematics. In: 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids), pp. 928\u2013935. IEEE (2015). \n                      https:\/\/doi.org\/10.1109\/HUMANOIDS.2015.7363472","DOI":"10.1109\/HUMANOIDS.2015.7363472"},{"key":"47_CR3","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9320.001.0001","volume-title":"Developmental Robotics: From Babies to Robots","author":"A Cangelosi","year":"2015","unstructured":"Cangelosi, A., Schlesinger, M.: Developmental Robotics: From Babies to Robots. MIT Press, Cambridge (2015). \n                      https:\/\/doi.org\/10.7551\/mitpress\/9320.001.0001"},{"key":"47_CR4","unstructured":"Chollet, F., et al.: Keras (2015). \n                      https:\/\/github.com\/keras-team\/keras"},{"issue":"03","key":"47_CR5","doi-asserted-by":"publisher","first-page":"230","DOI":"10.4236\/jsea.2010.33028","volume":"3","author":"B Daya","year":"2010","unstructured":"Daya, B., Khawandi, S., Akoum, M.: Applying neural network architecture for inverse kinematics problem in robotics. J. Softw. Eng. Appl. 3(03), 230 (2010). \n                      https:\/\/doi.org\/10.4236\/jsea.2010.33028","journal-title":"J. Softw. Eng. Appl."},{"key":"47_CR6","unstructured":"Gu, S., Lillicrap, T., Sutskever, I., Levine, S.: Continuous deep Q-learning with model-based acceleration. In: International Conference on Machine Learning, pp. 2829\u20132838 (2016). \n                      http:\/\/dl.acm.org\/citation.cfm?id=3045390.3045688"},{"key":"47_CR7","doi-asserted-by":"publisher","unstructured":"Hafez, B., Weber, C., Wermter, S.: Curiosity-driven exploration enhances motor skills of continuous actor-critic learner. In: Proceedings of the 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob), pp. 39\u201346 (2017). \n                      https:\/\/doi.org\/10.1109\/DEVLRN.2017.8329785","DOI":"10.1109\/DEVLRN.2017.8329785"},{"issue":"1","key":"47_CR8","doi-asserted-by":"publisher","first-page":"52","DOI":"10.11591\/ijra.v3i1.3201","volume":"3","author":"P Jha","year":"2014","unstructured":"Jha, P., Biswal, B.: A neural network approach for inverse kinematic of a scara manipulator. IAES Int. J. Rob. Autom. 3(1), 52 (2014). \n                      https:\/\/doi.org\/10.11591\/ijra.v3i1.3201","journal-title":"IAES Int. J. Rob. Autom."},{"key":"47_CR9","doi-asserted-by":"publisher","unstructured":"Kerzel, M., Beik-Mohammadi, H., Zamani, M.A., Wermter, S.: Accelerating deep continuous reinforcement learning through task simplification (2018). \n                      https:\/\/doi.org\/10.1109\/IJCNN.2018.8489712","DOI":"10.1109\/IJCNN.2018.8489712"},{"key":"47_CR10","series-title":"Springer Proceedings in Advanced Robotics","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/978-3-319-50115-4_16","volume-title":"2016 International Symposium on Experimental Robotics","author":"S Levine","year":"2017","unstructured":"Levine, S., Pastor, P., Krizhevsky, A., Quillen, D.: Learning hand-eye coordination for robotic grasping with large-scale data collection. In: Kuli\u0107, D., Nakamura, Y., Khatib, O., Venture, G. (eds.) ISER 2016. SPAR, vol. 1, pp. 173\u2013184. Springer, Cham (2017). \n                      https:\/\/doi.org\/10.1007\/978-3-319-50115-4_16"},{"key":"47_CR11","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint \n                      arXiv:1509.02971\n                      \n                     (2015)"},{"key":"47_CR12","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/S0079-7421(08)60536-8","volume":"24","author":"M McCloskey","year":"1989","unstructured":"McCloskey, M., Cohen, N.J.: Catastrophic interference in connectionist networks: the sequential learning problem. Psychol. Learn. Motiv. 24, 109\u2013165 (1989). \n                      https:\/\/doi.org\/10.1016\/S0079-7421(08)60536-8","journal-title":"Psychol. Learn. Motiv."},{"issue":"7540","key":"47_CR13","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015). \n                      https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"issue":"1","key":"47_CR14","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/BF00993104","volume":"13","author":"AW Moore","year":"1993","unstructured":"Moore, A.W., Atkeson, C.G.: Prioritized sweeping: reinforcement learning with less data and less time. Mach. Learn. 13(1), 103\u2013130 (1993). \n                      https:\/\/doi.org\/10.1007\/BF00993104","journal-title":"Mach. Learn."},{"key":"47_CR15","unstructured":"Ng, A.Y., Harada, D., Russell, S.J.: Policy invariance under reward transformations: theory and application to reward shaping. In: Proceedings of the Sixteenth International Conference on Machine Learning, pp. 278\u2013287, ICML 1999. Morgan Kaufmann Publishers Inc., San Francisco (1999). \n                      http:\/\/dl.acm.org\/citation.cfm?id=645528.657613"},{"key":"47_CR16","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. arXiv preprint \n                      arXiv:1511.05952\n                      \n                     (2015)"},{"key":"47_CR17","doi-asserted-by":"publisher","unstructured":"Van Hasselt, H., Wiering, M.A.: Reinforcement learning in continuous action spaces. In: IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, ADPRL 2007, pp. 272\u2013279. IEEE (2007). \n                      https:\/\/doi.org\/10.1109\/ADPRL.2007.368199","DOI":"10.1109\/ADPRL.2007.368199"},{"issue":"3\u20134","key":"47_CR18","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3\u20134), 279\u2013292 (1992). \n                      https:\/\/doi.org\/10.1007\/BF00992698","journal-title":"Mach. Learn."}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2019: Theoretical Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-30487-4_47","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,8]],"date-time":"2019-09-08T19:16:00Z","timestamp":1567970160000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-30487-4_47"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030304867","9783030304874"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-30487-4_47","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"9 September 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}