Deep Attention Recurrent Q-Network
Authors:
- Ivan SorokinISIvan Sorokin
- Alexey SeleznevASAlexey Seleznev
- Mikhail PavlovMPMikhail Pavlov
- Aleksandr FedorovAFAleksandr Fedorov
- Anastasiia IgnatevaAIAnastasiia Ignateva
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 1 reference indexed in Scilit:
- Learning Where to Attend with Deep Architectures for Image TrackingNeural Computation, 2012