{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:27Z","timestamp":1760245047441,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319700861"},{"type":"electronic","value":"9783319700878"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","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":[[2017]]},"DOI":"10.1007\/978-3-319-70087-8_77","type":"book-chapter","created":{"date-parts":[[2017,10,23]],"date-time":"2017-10-23T21:10:19Z","timestamp":1508793019000},"page":"749-758","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Implicit Incremental Natural Actor Critic"],"prefix":"10.1007","author":[{"given":"Ryo","family":"Iwaki","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minoru","family":"Asada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,10,24]]},"reference":[{"issue":"2","key":"77_CR1","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1162\/089976698300017746","volume":"10","author":"S Amari","year":"1998","unstructured":"Amari, S.: Natural gradient works efficiently in learning. Neural Comput. 10(2), 251\u2013276 (1998)","journal-title":"Neural Comput."},{"issue":"11","key":"77_CR2","doi-asserted-by":"publisher","first-page":"2471","DOI":"10.1016\/j.automatica.2009.07.008","volume":"45","author":"S Bhatnagar","year":"2009","unstructured":"Bhatnagar, S., Sutton, R.S., Ghavamzadeh, M., Lee, M.: Natural actor-critic algorithms. Automatica 45(11), 2471\u20132482 (2009)","journal-title":"Automatica"},{"key":"77_CR3","unstructured":"Chou, P.W., Maturana, D., Scherer, S.: Improving stochastic policy gradients in continuous control with deep reinforcement learning using the beta distribution. In: Proceedings of the 34th International Conference on Machine Learning, PMLR, vol. 70 (2017)"},{"key":"77_CR4","unstructured":"Dabney, W., Barto, A.G.: Adaptive step-size for online temporal difference learning. In: AAAI (2012)"},{"key":"77_CR5","doi-asserted-by":"crossref","unstructured":"Degris, T., Pilarski, P.M., Sutton, R.S.: Model-free reinforcement learning with continuous action in practice. In: Proceedings of the 2012 American Control Conference (2012)","DOI":"10.1109\/ACC.2012.6315022"},{"key":"77_CR6","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1162\/089976600300015961","volume":"12","author":"K Doya","year":"2000","unstructured":"Doya, K.: Reinforcement learning in continuous time and space. Neural Comput. 12, 243\u2013269 (2000)","journal-title":"Neural Comput."},{"key":"77_CR7","unstructured":"Duan, Y., Chen, X., Houthooft, R., Schulman, J., Abbeel, P.: Benchmarking deep reinforcement learning for continuous control. In: Proceedings of the 33rd International Conference on Machine Learning, pp. 1329\u20131338 (2016)"},{"key":"77_CR8","first-page":"1471","volume":"5","author":"E Greensmith","year":"2004","unstructured":"Greensmith, E., Bartlett, P.L., Baxter, J.: Variance reduction techniques for gradient estimates in reinforcement learning. J. Mach. Learn. Res. 5, 1471\u20131530 (2004)","journal-title":"J. Mach. Learn. Res."},{"key":"77_CR9","doi-asserted-by":"crossref","unstructured":"Jurcicek, F., Thomson, B., Keizer, S., Mairesse, F., Gasic, M., Yu, K., Young, S.J.: Natural belief-critic: a reinforcement algorithm for parameter estimation in statistical spoken dialogue systems. In: Interspeech, pp. 90\u201393 (2010)","DOI":"10.21437\/Interspeech.2010-41"},{"key":"77_CR10","unstructured":"Kakade, S.: A natural policy gradient. In: Advances in Neural Information Processing Systems, vol. 14 (2001)"},{"key":"77_CR11","doi-asserted-by":"crossref","unstructured":"Konidaris, G., Osentoski, S., Thomas, P.: Value function approximation in reinforcement learning using the fourier basis. In: Proceedings of the National Conference on Artificial Intelligence (AAAI), pp. 380\u2013385 (2011)","DOI":"10.1609\/aaai.v25i1.7903"},{"key":"77_CR12","unstructured":"Matsubara, T., Morimura, T., Morimoto, J.: Adaptive step-size policy gradients with average reward metric. In: Journal of Machine Learning Research - Proceedings Track, vol. 13 (2010)"},{"key":"77_CR13","unstructured":"Morimura, T., Uchibe, E., Doya, K.: Utilizing natural gradient in temporal difference reinforcement learning with eligibility traces. In: International Symposium on Information Geometry and Its Applications, pp. 256\u2013263 (2005)"},{"key":"77_CR14","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, 1180\u20131190 (2008)","journal-title":"Neurocomputing"},{"key":"77_CR15","unstructured":"Peters, J., Vijayakumar, S., Schaal, S.: Reinforcement learning for humanoid robotics. In: Proceedings of the Third IEEE-RAS International Conference on Humanoid Robots, pp. 1\u201320. American Association for Artificial Intelligence (2003)"},{"key":"77_CR16","unstructured":"Pirotta, M., Restelli, M., Bascetta, L.: Adaptive step-size for policy gradient methods. In: Advances in Neural Information Processing Systems, pp. 1394\u20131402 (2013)"},{"key":"77_CR17","first-page":"1169","volume-title":"Advances in Neural Information Processing Systems","author":"S Richter","year":"2007","unstructured":"Richter, S., Aberdeen, D., Yu, J.: Natural actor-critic for road traffic optimisation. In: Sch\u00f6lkopf, P.B., Platt, J.C., Hoffman, T. (eds.) Advances in Neural Information Processing Systems, pp. 1169\u20131176. MIT Press, Cambridge (2007). http:\/\/papers.nips.cc\/paper\/3087-natural-actor-critic-for-road-traffic-optimisation.pdf"},{"key":"77_CR18","unstructured":"Schulman, J., Levine, S., Moritz, P., Jordan, M., Abbeel, P.: Trust region policy optimization. In: Proceedings of the 32nd International Conference on Machine Learning, pp. 1889\u20131897 (2015)"},{"key":"77_CR19","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: Proceedings of the 31st International Conference on Machine Learning, pp. 387\u2013395 (2014)"},{"key":"77_CR20","unstructured":"Sutton, R.S., McAllester, D., Singh, S., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems, vol. 12, pp. 1057\u20131063 (1999)"},{"key":"77_CR21","unstructured":"Tamar, A., Toulis, P., Mannor, S., Airoldi, E.M.: Implicit temporal differences. In: Neural Information Processing Systems, Workshop on Large-Scale Reinforcement Learning (2014)"},{"key":"77_CR22","unstructured":"Thomas, P.S.: Bias in natural actor-critic algorithms. In: Proceedings of The 31st International Conference on Machine Learning, pp. 441\u2013448 (2014)"},{"key":"77_CR23","unstructured":"Thomas, P.S.: Genga: a generalization of natural gradient ascent with positive and negative convergence results. In: Proceedings of The 31st International Conference on Machine Learning, pp. 1575\u20131583 (2014)"},{"key":"77_CR24","unstructured":"Toulis, P., Rennie, J., Airoldi, E.M.: Statistical analysis of stochastic gradient methods for generalized linear models. In: Proceedings of The 31st International Conference on Machine Learning, vol. 32(1), pp. 667\u2013675 (2014)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-70087-8_77","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T15:24:52Z","timestamp":1710343492000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-70087-8_77"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319700861","9783319700878"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-70087-8_77","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"24 October 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guangzhou","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":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 November 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.iconip2017.org\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}