Towards Playing a 3D First-Person Shooter Game Using a Classification Deep Neural Network Architecture

In this work, we present a network architecture to solve a supervised learning problem, the classification of a handwritten dataset, and a reinforcement learning problem, a complex First-Person Shooter 3D game environment. We used a Deep Neural Network model to solve both problems. For classification, we used a Softmax regression and cross entropy loss to train the network. To play the game, we used a Q-Learning adaptation for Deep Learning to train the autonomous agent. In both cases, the input was only the pixels of an image. We show that this single network architecture is suitable for the classification task and is capable of playing the 3D game. This result gives us an insight into the possibility of a general network architecture, capable of solving any kind of problems, regardless of the learning paradigm.

[1]  Hado van Hasselt,et al.  Double Q-learning , 2010, NIPS.

[2]  Shane Legg,et al.  Massively Parallel Methods for Deep Reinforcement Learning , 2015, ArXiv.

[3]  Alex Graves,et al.  Playing Atari with Deep Reinforcement Learning , 2013, ArXiv.

[4]  Guillaume Lample,et al.  Playing FPS Games with Deep Reinforcement Learning , 2016, AAAI.

[5]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[6]  George E. Nasr,et al.  Cross Entropy Error Function in Neural Networks: Forecasting Gasoline Demand , 2002, FLAIRS.

[7]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[8]  Yann LeCun,et al.  Regularization of Neural Networks using DropConnect , 2013, ICML.

[9]  Wojciech Jaskowski,et al.  ViZDoom: A Doom-based AI research platform for visual reinforcement learning , 2016, 2016 IEEE Conference on Computational Intelligence and Games (CIG).

[10]  David Silver,et al.  Deep Reinforcement Learning with Double Q-Learning , 2015, AAAI.

[11]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[12]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[13]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[14]  Long-Ji Lin,et al.  Reinforcement learning for robots using neural networks , 1992 .

[15]  Alex Graves,et al.  Asynchronous Methods for Deep Reinforcement Learning , 2016, ICML.

[16]  Peter Stone,et al.  Deep Reinforcement Learning in Parameterized Action Space , 2015, ICLR.

[17]  Simon Haykin,et al.  GradientBased Learning Applied to Document Recognition , 2001 .

[18]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[19]  Lawrence Carin,et al.  Sparse multinomial logistic regression: fast algorithms and generalization bounds , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Ruslan Salakhutdinov,et al.  Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning , 2015, ICLR.

[21]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[22]  Chris Watkins,et al.  Learning from delayed rewards , 1989 .

[23]  Tom Schaul,et al.  Dueling Network Architectures for Deep Reinforcement Learning , 2015, ICML.

[24]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[25]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..