除了强化学习的方式,完成FlappyBird游戏也可以采用其他方法,如论文Exploring Game Space Using Survival Analysis的通过生存分析的方法,有兴趣的可以查阅原文。由于博主能力有限,博文中提及的方法与代码即使经过测试,也难免会有疏漏之处。希望您能热心指出其中的错误,以便下次修改时能以一个更完美更严谨的样子,呈现在大家面前。同时如果有更好的实现方法也请您不吝赐教。
参考文献: [1] C. Clark and A. Storkey. Teaching deep convolutional neural networks to play go. arXiv preprint arXiv:1412.3409, 2014. 1, 2 [2] V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, and M. Riedmiller. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602, 2013. 1, 2 [3] V. Mnih, K. Kavukcuoglu, D. Silver, A. A. Rusu, J. Veness, M. G. Bellemare, A. Graves, M. Riedmiller, A. K. Fidjeland, G. Ostrovski, et al. Human-level control through deep reinforcement learning. Nature, 518(7540):529–533, 2015. 3, 5 [4] D. Silver, A. Huang, C. J. Maddison, A. Guez, L. Sifre, G. van den Driessche, J. Schrittwieser, I. Antonoglou, V. Panneershelvam, M. Lanctot, et al. Mastering the game of go with deep neural networks and tree search. Nature, 529(7587):484–489, 2016. 1