Deep Attention Recurrent Q-Network
This work addresses performance enhancement in reinforcement learning for game-playing agents, representing an incremental improvement over DQN.
The authors tackled the problem of improving reinforcement learning for visual input tasks by extending the Deep Q-Network (DQN) with attention mechanisms, resulting in the Deep Attention Recurrent Q-Network (DARQN) that outperforms DQN on multiple Atari 2600 games.
A deep learning approach to reinforcement learning led to a general learner able to train on visual input to play a variety of arcade games at the human and superhuman levels. Its creators at the Google DeepMind's team called the approach: Deep Q-Network (DQN). We present an extension of DQN by "soft" and "hard" attention mechanisms. Tests of the proposed Deep Attention Recurrent Q-Network (DARQN) algorithm on multiple Atari 2600 games show level of performance superior to that of DQN. Moreover, built-in attention mechanisms allow a direct online monitoring of the training process by highlighting the regions of the game screen the agent is focusing on when making decisions.