In reinforcement learning, the traditional Q Learning method solves the game by iterating over the full set of states. Using the Q-Table to implement QLearning is fine in small discrete environments. However often we realize that we have too many states to track. An example is Atari games, that can have a large variety of different screens, and in this case, the problem cannot be solved with a Q-table. This paper uses a deep neural network instead of a Q-table to solve it. Atari games are displayed at a resolution of 210 by 160 pixels, with 128 possible colors for each pixel. This is still technically a discrete state space but very large to process. To reduce this complexity, we performed some minimal image preprocessing. Finally, from the experimental results, it is concluded that DQN can make the agent get high scores from Atari game, and experience replay can make the model training better.

Keywords : Deep Reinforcement Learning; Artificial Intelligence; Image Processing