Playing Atari with Deep Reinforcement Learning
Abstract: We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards. We apply our method to seven Atari 2600 games from the Arcade Learning Environment, with no adjustment of the architecture or learning algorithm. We find that it outperforms all previous approaches on six of the games and surpasses a human expert on three of them.
Paper Link: https://arxiv.org/pdf/1312.5602.pdf
1. Perform pre-processing steps as mentioned in the paper.
2. Implement Algorithm 1, Deep Q-learning with Experience Replay
3. Plot average reward per episode on any two Atari 2600 Games respectively during training as shown in Figure 2
Dataset: For A.L.E: Atari 2600 Learning Environment, refer here: http://yavar.naddaf.name/ale/