{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T12:48:31Z","timestamp":1725886111817},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319579689"},{"type":"electronic","value":"9783319579696"}],"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":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-57969-6_6","type":"book-chapter","created":{"date-parts":[[2017,4,28]],"date-time":"2017-04-28T10:04:26Z","timestamp":1493373866000},"page":"71-85","source":"Crossref","is-referenced-by-count":0,"title":["Learning from the Memory of Atari 2600"],"prefix":"10.1007","author":[{"given":"Jakub","family":"Sygnowski","sequence":"first","affiliation":[]},{"given":"Henryk","family":"Michalewski","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,4,29]]},"reference":[{"key":"6_CR1","unstructured":"The Bowling Manual. https:\/\/atariage.com\/manual_html_page.php?SoftwareID=879"},{"key":"6_CR2","unstructured":"Bowling (video game). https:\/\/en.wikipedia.org\/wiki\/Bowling_(video_game)"},{"key":"6_CR3","unstructured":"The Breakout Manual. https:\/\/atariage.com\/manual_html_page.php?SoftwareID=889"},{"key":"6_CR4","unstructured":"Breakout (video game). https:\/\/en.wikipedia.org\/wiki\/Breakout_(video_game)"},{"key":"6_CR5","unstructured":"Lasagne - lightweight library to build and train neural networks in Theano. https:\/\/github.com\/lasagne\/lasagne"},{"key":"6_CR6","unstructured":"Nathan Sprague\u2019s implementation of DQN. https:\/\/github.com\/spragunr\/deep_q_rl"},{"key":"6_CR7","unstructured":"The repository of our code. https:\/\/github.com\/sygi\/deep_q_rl"},{"key":"6_CR8","unstructured":"The Seaquest manual. https:\/\/atariage.com\/manual_html_page.html?SoftwareLabelID=424"},{"key":"6_CR9","unstructured":"Seaquest (video game). https:\/\/en.wikipedia.org\/wiki\/Seaquest_(video_game)"},{"issue":"2","key":"6_CR10","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/0890-5401(87)90052-6","volume":"75","author":"D Angluin","year":"1987","unstructured":"Angluin, D.: Learning regular sets from queries and counterexamples. Inf. Comput. 75(2), 87\u2013106 (1987)","journal-title":"Inf. Comput."},{"key":"6_CR11","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Bergstra, J., Breuleux, O., Bastien, F., Lamblin, P., Pascanu, R., Desjardins, G., Turian, J., Warde-Farley, D., Bengio, Y.: Theano: a CPU and GPU math expression compiler. In: Proceedings of the Python for Scientific Computing Conference (SciPy), Oral Presentation (2010)","DOI":"10.25080\/Majora-92bf1922-003"},{"key":"6_CR13","unstructured":"Braylan, A., Hollenbeck, M., Meyerson, E., Miikkulainen, R.: Frame skip is a powerful parameter for learning to play Atari. In: AAAI-15 Workshop on Learning for General Competency in Video Games (2015)"},{"key":"6_CR14","unstructured":"Defazio, A., Graepel, T.: A comparison of learning algorithms on the Arcade learning environment. CoRR abs\/1410.8620 (2014). http:\/\/arxiv.org\/abs\/1410.8620"},{"key":"6_CR15","unstructured":"Liang, Y., Machado, M.C., Talvitie, E., Bowling, M.: State of the art control of Atari games using shallow reinforcement learning. arXiv preprint arXiv:1512.01563 (2015)"},{"key":"6_CR16","unstructured":"Lipovetzky, N., Ramirez, M., Geffner, H.: Classical planning with simulators: results on the Atari video games. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 1610\u20131616 (2015)"},{"key":"6_CR17","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing Atari with deep reinforcement learning. In: NIPS Deep Learning Workshop (2013)"},{"issue":"7540","key":"6_CR18","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., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., Hassabis, D.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"6_CR19","volume-title":"Artificial Intelligence - A Modern Approach","author":"SJ Russell","year":"2010","unstructured":"Russell, S.J., Norvig, P.: Artificial Intelligence - A Modern Approach, 3 internat edn. Pearson Education, Englewood Cliffs (2010)","edition":"3 internat"},{"key":"6_CR20","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. arXiv preprint arXiv:1509.06461 (2015)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"6_CR22","doi-asserted-by":"publisher","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine Learning. ICML 2008, pp. 1096\u20131103. ACM, New York (2008)","DOI":"10.1145\/1390156.1390294"},{"key":"6_CR23","unstructured":"Wang, Z., Schaul, T., Hessel, M., van Hasselt, H., Lanctot, M., de Freitas, N.: Dueling network architectures preprint arXiv:1511.06581 (2015)"},{"key":"6_CR24","unstructured":"Warde-Farley, D., Goodfellow, I.J., Courville, A., Bengio, Y.: An empirical analysis of dropout in piecewise linear networks. In: ICLR 2014 (2014)"},{"key":"6_CR25","first-page":"279","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Technical note Q-learning. Mach. Learn. 8, 279\u2013292 (1992)","journal-title":"Mach. Learn."}],"container-title":["Communications in Computer and Information Science","Computer Games"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-57969-6_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T09:48:21Z","timestamp":1692784101000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-57969-6_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319579689","9783319579696"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-57969-6_6","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2017]]}}}