Free-Lunch Saliency via Attention in Atari Agents

by   Dmitry Nikulin, et al.

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 (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.


page 5

page 6

page 8


Benchmarking Perturbation-based Saliency Maps for Explaining Deep Reinforcement Learning Agents

Recent years saw a plethora of work on explaining complex intelligent ag...

Explain Your Move: Understanding Agent Actions Using Focused Feature Saliency

As deep reinforcement learning (RL) is applied to more tasks, there is a...

Human versus Machine Attention in Deep Reinforcement Learning Tasks

Deep reinforcement learning (RL) algorithms are powerful tools for solvi...

Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep RL

Saliency maps have been used to support explanations of deep reinforceme...

Quality-Aware Multimodal Saliency Detection via Deep Reinforcement Learning

Incorporating various modes of information into the machine learning pro...

Interpretability for Conditional Coordinated Behavior in Multi-Agent Reinforcement Learning

We propose a model-free reinforcement learning architecture, called dist...

Picasso: A Modular Framework for Visualizing the Learning Process of Neural Network Image Classifiers

Picasso is a free open-source (Eclipse Public License) web application w...

Please sign up or login with your details

Forgot password? Click here to reset