{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T21:36:43Z","timestamp":1726004203057},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030013691"},{"type":"electronic","value":"9783030013707"}],"license":[{"start":{"date-parts":[[2018,12,31]],"date-time":"2018-12-31T00:00:00Z","timestamp":1546214400000},"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\/978-3-030-01370-7_32","type":"book-chapter","created":{"date-parts":[[2018,12,31]],"date-time":"2018-12-31T00:53:36Z","timestamp":1546217616000},"page":"401-413","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Simulation and Transfer of Reinforcement Learning Algorithms for Autonomous Obstacle Avoidance"],"prefix":"10.1007","author":[{"given":"Max","family":"Lenk","sequence":"first","affiliation":[]},{"given":"Paula","family":"Hilsendegen","sequence":"additional","affiliation":[]},{"given":"Silvan Michael","family":"M\u00fcller","sequence":"additional","affiliation":[]},{"given":"Oliver","family":"Rettig","sequence":"additional","affiliation":[]},{"given":"Marcus","family":"Strand","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,12,31]]},"reference":[{"key":"32_CR1","volume-title":"Introduction to Autonomous Mobile Robots","author":"R Siegwart","year":"2011","unstructured":"Siegwart, R., Nourbakhsh, I.R., Scaramuzza, D.: Introduction to Autonomous Mobile Robots. MIT Press, Cambridge (2011)"},{"issue":"11","key":"32_CR2","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1177\/0278364913495721","volume":"32","author":"J Kober","year":"2013","unstructured":"Kober, J., Bagnell, J.A., Peters, J.: Reinforcement learning in robotics: a survey. Int. J. Rob. Res. 32(11), 1238\u20131274 (2013)","journal-title":"Int. J. Rob. Res."},{"key":"32_CR3","unstructured":"Azouaoui, O.: Reinforcement learning (RL) based collision avoidance approach for multiple Autonomous Robotic Systems (ARS). In: Proceedings 10th IEEE International Conference on Advanced Robotics, pp. 561\u2013566 (2001)"},{"key":"32_CR4","unstructured":"Xie, L., Wang, S., Markham, A., Trigoni, N.: Towards monocular vision based obstacle avoidance through deep reinforcement learning. arXiv preprint arXiv:1706.09829 (2017)"},{"key":"32_CR5","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, vol. 1, No. 1. MIT Press, Cambridge (1998)"},{"key":"32_CR6","unstructured":"Thorndike, E.L.: Laws and hypotheses for behavior. In: Thorndike, E.L. (ed.) Animal Intelligence, pp. 241\u2013281 (1970)"},{"issue":"3","key":"32_CR7","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1016\/S0163-6383(02)00097-8","volume":"25","author":"A Needham","year":"2002","unstructured":"Needham, A., Barrett, T., Peterman, K.: A pick-me-up for infants\u2019 exploratory skills: early simulated experiences reaching for objects using \u2018sticky mittens\u2019 enhances young infants\u2019 object exploration skills. Infant Behav. Dev. 25(3), 279\u2013295 (2002)","journal-title":"Infant Behav. Dev."},{"issue":"1","key":"32_CR8","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1901\/jeab.1986.45-115","volume":"45","author":"BF Skinner","year":"1986","unstructured":"Skinner, B.F.: The evolution of verbal behavior. J. Exp. Anal. Behav. 45(1), 115\u2013122 (1986)","journal-title":"J. Exp. Anal. Behav."},{"issue":"22","key":"32_CR9","doi-asserted-by":"publisher","first-page":"11850","DOI":"10.1073\/pnas.97.22.11850","volume":"97","author":"PK Kuhl","year":"2000","unstructured":"Kuhl, P.K.: A new view of language acquisition. Proc. Nat. Acad. Sci. 97(22), 11850\u201311857 (2000)","journal-title":"Proc. Nat. Acad. Sci."},{"issue":"4","key":"32_CR10","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1037\/0033-295X.109.4.679","volume":"109","author":"CB Holroyd","year":"2002","unstructured":"Holroyd, C.B., Coles, M.G.: The neural basis of human error processing: reinforcement learning, dopamine, and the error-related negativity. Psychol. Rev. 109(4), 679 (2002)","journal-title":"Psychol. Rev."},{"issue":"4","key":"32_CR11","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1016\/0921-8890(95)00022-8","volume":"15","author":"S Thrun","year":"1995","unstructured":"Thrun, S.: An approach to learning mobile robot navigation. Rob. Autonom. Syst. 15(4), 301\u2013319 (1995)","journal-title":"Rob. Autonom. Syst."},{"issue":"4","key":"32_CR12","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1016\/j.neunet.2008.02.003","volume":"21","author":"J Peters","year":"2008","unstructured":"Peters, J., Schaal, S.: Reinforcement learning of motor skills with policy gradients. Neural Netw. 21(4), 682\u2013697 (2008)","journal-title":"Neural Netw."},{"key":"32_CR13","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-01551-9","volume-title":"Reinforcement Learning Algorithms for MDPs","author":"C Szepesv\u00e1ri","year":"2010","unstructured":"Szepesv\u00e1ri, C.: Reinforcement Learning Algorithms for MDPs. Morgan and Claypool Publishers, San Rafael (2010)"},{"issue":"3\u20134","key":"32_CR14","first-page":"279","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3\u20134), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"32_CR15","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning. Technical report arXiv:1312.5602 [cs.LG], Deepmind Technologies (2013)"},{"key":"32_CR16","unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., Wierstra, D.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"issue":"7","key":"32_CR17","doi-asserted-by":"publisher","first-page":"1180","DOI":"10.1016\/j.neucom.2007.11.026","volume":"71","author":"J Peters","year":"2008","unstructured":"Peters, J., Schaal, S.: Natural actor-critic. Neurocomputing 71(7), 1180\u20131190 (2008)","journal-title":"Neurocomputing"},{"key":"32_CR18","unstructured":"Mnih, V., Badia, A.P., Mirza, M., Graves, A., Lillicrap, T.P., Harley, T., Silver, D., Kavukcuoglu, K.: Asynchronous methods for deep reinforcement learning. In International Conference on Machine Learning, pp. 1928\u20131937 (2016)"},{"key":"32_CR19","unstructured":"Palamuttam, R., Chen, W.: Vision enhanced asynchronous advantage actor-critic on racing games. Methods 4, A3C (2017)"},{"key":"32_CR20","unstructured":"Mirowski, P., Pascanu, R., Viola, F., Soyer, H., Ballard, A., Banino, A., Denil, M., Goroshin, R., Sifre, L., Kavukcuoglu, K., Hadsell, R., Kumaran, D.: Learning to navigate in complex environments (2016). arXiv preprint arXiv:1611.03673"},{"key":"32_CR21","unstructured":"Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., Tang, J., Zaremba, W.: OpenAI gym (2016). arXiv preprint arXiv:1606.01540"},{"key":"32_CR22","unstructured":"Racaniere, S., Weber, T., Reichert, D.P., Buesing, L., Guez, A., Rezende, D., Badia, A.P., Vinyals, O., Heess, N., Li, Y., Pascanu, R., Battaglia, P., Hassabis, D., Silver, D., Wierstra, D.: Imagination-augmented agents for deep reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 5694\u20135705 (2017)"}],"container-title":["Advances in Intelligent Systems and Computing","Intelligent Autonomous Systems 15"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01370-7_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,9]],"date-time":"2022-09-09T10:10:59Z","timestamp":1662718259000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-01370-7_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,31]]},"ISBN":["9783030013691","9783030013707"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01370-7_32","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2018,12,31]]},"assertion":[{"value":"IAS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Autonomous Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Baden-Baden","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":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 June 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 June 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ias2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/conference.vde.com\/ias\/Pages\/Homepage.aspx","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}