An initial attempt of combining visual selective attention with deep reinforcement learning
This work addresses sample efficiency for reinforcement learning practitioners, but it is incremental as it builds on existing attention and DRL methods.
The paper tackled the problem of improving sample efficiency in deep reinforcement learning by integrating visual selective attention mechanisms, showing that this combination led to improvements in sample efficiency on tested Atari games.
Visual attention serves as a means of feature selection mechanism in the perceptual system. Motivated by Broadbent's leaky filter model of selective attention, we evaluate how such mechanism could be implemented and affect the learning process of deep reinforcement learning. We visualize and analyze the feature maps of DQN on a toy problem Catch, and propose an approach to combine visual selective attention with deep reinforcement learning. We experiment with optical flow-based attention and A2C on Atari games. Experiment results show that visual selective attention could lead to improvements in terms of sample efficiency on tested games. An intriguing relation between attention and batch normalization is also discovered.