Free-Lunch Saliency via Attention in Atari Agents
By Dmitry Nikulin, Anastasia Ianina, Vladimir Aliev, Sergey I. Nikolenko. 2019
28 citations recorded by the source corpus.
We propose a new approach to visualize saliency maps for deep neural network models and apply it to deep reinforcement learning agents trained on Atari environments. Our method adds an attention module that we call FLS (Free Lunch Saliency) to the feature extractor from an established baseline of Mnih et al, 2015. This addition results in a trainable model that can produce saliency maps, i.e., visualizations of the importance of different parts of the input for the agent's current decision making. We show experimentally that a network with an FLS module exhibits performance similar to the baseline (i.e., it is “free”, with no performance cost) and can be used as a drop-in replacement for reinforcement learning agents. We also design another feature extractor that scores slightly lower but provides higher-fidelity visualizations. In addition to attained scores, we report saliency metrics evaluated on the Atari-HEAD dataset of human gameplay.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Akanksha Atrey
- Kaleigh Clary
- David D. Jensen
- Ruohan Zhang
- Lin Guan
- Dana H. Ballard
- Zhuode Liu
- Mary M. Hayhoe
In Computer Vision and Pattern Recognition
- Ruohan Zhang
- Dana H. Ballard
- Mary M. Hayhoe
- Lin Guan
- David D. Jensen
- Luxin Zhang
- Zhuode Liu
- Akanksha Atrey
Citations in the corpus
- Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning (2019, background): “Most recently, attention-based saliency mapping methods have been proposed to generate interpretable saliency maps (Mott et al., 2019; Nikulin et al., 2019).”
- Atari-HEAD: Atari Human Eye-Tracking and Demonstration Dataset (2019, background): “Although deep RL agents have achieved great performance on many tasks, researchers have attempted to understand these agents’ behaviors through visualizing feature saliency maps learned by the deep network (Mousavi, Borji, and Mozayani 2016; Nikulin et al. 2019).”