Automating Pacman with Deep Q-Learning Using PYgame

[1] S. Adam, L. Bu¸soniu, R. Babuˇska, Systems Man and Cybernetics Part C: Applications and Reviews IEEE
Transactions on 2012, 42, 201–212.
[2] M. G. Bellemare, Y. Naddaf, J. Veness, M. Bowling, Journal of Artificial Intelligence Research 2012. [3] R. Bellman,
Indiana Univ. Math. J. 1957, 6, 679–684.
[4] R. E. Bellman, S. E. Dreyfus, Applied dynamic programming, Princeton university press, 2015.
[5] Berkeley Pacman project, http://ai.berkeley.edu/project_overview.html.
[6] T. J. Davidson, F. Kloosterman, M. A. Wilson, Neuron 2009, 63, 497–507.
[7] J. DeNero, D. Klein in Proceedings of the Symposium on Educational Advances in Artificial Intelligence, 2010.
[8] Google, Tensorflow, https : / / www . tensorflow . org / versions / r0 . 8 / get _ started / index.html, 2016.
[9] D. H. Hubel, T. N. Wiesel, The Journal of physiology 1968, 195, 215–243.
[10] A. Krizhevsky, I. Sutskever, G. E. Hinton in Advances in neural information processing systems, 2012, pp. 1097–1105