{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T18:59:43Z","timestamp":1725562783505},"publisher-location":"Berlin, Heidelberg","reference-count":19,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642158216"},{"type":"electronic","value":"9783642158223"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-15822-3_14","type":"book-chapter","created":{"date-parts":[[2010,8,12]],"date-time":"2010-08-12T11:21:34Z","timestamp":1281612094000},"page":"114-123","source":"Crossref","is-referenced-by-count":3,"title":["Multi-Dimensional Deep Memory Atari-Go Players for Parameter Exploring Policy Gradients"],"prefix":"10.1007","author":[{"given":"Mandy","family":"Gr\u00fcttner","sequence":"first","affiliation":[]},{"given":"Frank","family":"Sehnke","sequence":"additional","affiliation":[]},{"given":"Tom","family":"Schaul","sequence":"additional","affiliation":[]},{"given":"J\u00fcrgen","family":"Schmidhuber","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"14_CR1","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1109\/CIG.2006.311699","volume-title":"IEEE 2006 Symposium on Computational Intelligence in Games","author":"B. Bouzy","year":"2006","unstructured":"Bouzy, B., Chaslot, G.: Monte-Carlo Go Reinforcement Learning Experiments. In: IEEE 2006 Symposium on Computational Intelligence in Games, pp. 187\u2013194. IEEE, Los Alamitos (2006)"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Gelly, S., Silver, D.: Combining online and offline knowledge in UCT. In: ICML, vol.\u00a0227 (2007)","DOI":"10.1145\/1273496.1273531"},{"key":"14_CR3","unstructured":"Gr\u00fcttner, M.: Evolving Multidimensional Recurrent Neural Networks for the Capture Game in Go (2008)"},{"key":"14_CR4","unstructured":"Graves, A.: Supervised Sequence Labelling with Recurrent Neural Networks. PhD thesis, Technische Universit\u00e4t M\u00fcnchen (2007)"},{"key":"14_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1007\/978-3-642-04274-4_103","volume-title":"Artificial Neural Networks \u2013 ICANN 2009","author":"T. Schaul","year":"2009","unstructured":"Schaul, T., Schmidhuber, J.: Scalable neural networks for board games. In: Alippi, C., et al. (eds.) ICANN 2009. LNCS, vol.\u00a05768, pp. 1005\u20131014. Springer, Heidelberg (2009)"},{"key":"14_CR6","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1162\/106365601750190398","volume":"9","author":"N. Hansen","year":"2001","unstructured":"Hansen, N., Ostermeier, A.: Completely derandomized self-adaptation in evolution strategies. Evolutionary Computation\u00a09, 159\u2013195 (2001)","journal-title":"Evolutionary Computation"},{"key":"14_CR7","volume-title":"Evolution and optimum seeking","author":"H. Schwefel","year":"1995","unstructured":"Schwefel, H.: Evolution and optimum seeking. Wiley, New York (1995)"},{"key":"14_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/978-3-540-87536-9_40","volume-title":"Artificial Neural Networks - ICANN 2008","author":"F. Sehnke","year":"2008","unstructured":"Sehnke, F., Osendorfer, C., R\u00fcckstie\u00df, T., Graves, A., Peters, J., Schmidhuber, J.: Policy gradients with parameter-based exploration for control. In: K\u016frkov\u00e1, V., Neruda, R., Koutn\u00edk, J. (eds.) ICANN 2008, Part I. LNCS, vol.\u00a05163, pp. 387\u2013396. Springer, Heidelberg (2008)"},{"issue":"1","key":"14_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2478\/s13230-010-0002-4","volume":"1","author":"T. R\u00fcckstie\u00df","year":"2010","unstructured":"R\u00fcckstie\u00df, T., Sehnke, F., Schaul, T., Wierstra, D., Sun, Y., Schmidhuber, J.: Exploring parameter space in reinforcement learning. Paladyn\u00a01(1), 1\u201312 (2010)","journal-title":"Paladyn"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Schaul, T., Schmidhuber, J.: A scalable neural network architecture for board games. In: Proceedings of the IEEE Symposium on Computational Intelligence in Games (CIG 2008) (2008)","DOI":"10.1109\/CIG.2008.5035662"},{"key":"14_CR11","unstructured":"Konidaris, G., Shell, D., Oren, N.: Evolving Neural Networks for the Capture Game. In: Proceedings of the SAICSIT Postgraduate Symposium (2002)"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Stanley, K.O., Miikkulainen, R.: Evolving a Roving Eye for Go (2004)","DOI":"10.1007\/978-3-540-24855-2_130"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Schmidhuber, J.: Multi-Dimensional Recurrent Neural Networks (2007)","DOI":"10.1007\/978-3-540-74690-4_56"},{"key":"14_CR14","unstructured":"Liwicki, M., Graves, A., Fern\u00e1ndez, S., Bunke, H., Schmidhuber, J.: A novel approach to on-line handwriting recognition based on bidirectional long short-term memory networks. In: Proc. 9th Int. Conf. on Document Analysis and Recognition, pp. 367\u2013371 (September 2007)"},{"key":"14_CR15","first-page":"1521","volume-title":"Advances in Neural Information Processing Systems","author":"L. Wu","year":"2007","unstructured":"Wu, L., Baldi, P.: A scalable machine learning approach to go. In: Advances in Neural Information Processing Systems, vol.\u00a019, pp. 1521\u20131528. MIT Press, Cambridge (2007)"},{"key":"14_CR16","unstructured":"Streichert, F., Ulmer, H.: JavaEvA - A Java Framework for Evolutionary Algorithms. Technical Report WSI-2005-06, Centre for Bioinformatics T\u00fcbingen, University of T\u00fcbingen (2005)"},{"key":"14_CR17","unstructured":"Streichert, F.: Evolutionary Algorithms in Multi-Modal and Multi-Objective Environments. PhD thesis (2007)"},{"issue":"4","key":"14_CR18","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1016\/j.neunet.2009.12.004","volume":"23","author":"F. Sehnke","year":"2010","unstructured":"Sehnke, F., Osendorfer, C., R\u00fcckstie\u00df, T., Graves, A., Peters, J., Schmidhuber, J.: Parameter-exploring policy gradients. Neural Networks\u00a023(4), 551\u2013559 (2010)","journal-title":"Neural Networks"},{"key":"14_CR19","first-page":"743","volume":"11","author":"T. Schaul","year":"2010","unstructured":"Schaul, T., Bayer, J., Wierstra, D., Sun, Y., Felder, M., Sehnke, F., R\u00fcckstie\u00df, T., Schmidhuber, J.: PyBrain. Journal of Machine Learning Research\u00a011, 743\u2013746 (2010)","journal-title":"Journal of Machine Learning Research"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks \u2013 ICANN 2010"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-15822-3_14.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T02:40:58Z","timestamp":1606185658000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-15822-3_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642158216","9783642158223"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-15822-3_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}