Human versus Machine Attention in Deep Reinforcement Learning Tasks

by   Ruohan Zhang, et al.

Deep reinforcement learning (RL) algorithms are powerful tools for solving visuomotor decision tasks. However, the trained models are often difficult to interpret, because they are represented as end-to-end deep neural networks. In this paper, we shed light on the inner workings of such trained models by analyzing the pixels that they attend to during task execution, and comparing them with the pixels attended to by humans executing the same tasks. To this end, we investigate the following two questions that, to the best of our knowledge, have not been previously studied. 1) How similar are the visual features learned by RL agents and humans when performing the same task? and, 2) How do similarities and differences in these learned features correlate with RL agents' performance on these tasks? Specifically, we compare the saliency maps of RL agents against visual attention models of human experts when learning to play Atari games. Further, we analyze how hyperparameters of the deep RL algorithm affect the learned features and saliency maps of the trained agents. The insights provided by our results have the potential to inform novel algorithms for the purpose of closing the performance gap between human experts and deep RL agents.


page 5

page 12

page 14

page 19

page 22

page 23

page 25

page 26


An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents

Much human and computational effort has aimed to improve how deep reinfo...

Generating Explanations from Deep Reinforcement Learning Using Episodic Memory

Deep Reinforcement Learning (RL) involves the use of Deep Neural Network...

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

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

Visualizing and Understanding Atari Agents

Deep reinforcement learning (deep RL) agents have achieved remarkable su...

Free-Lunch Saliency via Attention in Atari Agents

We propose a new approach to visualize saliency maps for deep neural net...

Explain Your Move: Understanding Agent Actions Using Focused Feature Saliency

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

Selective Particle Attention: Visual Feature-Based Attention in Deep Reinforcement Learning

The human brain uses selective attention to filter perceptual input so t...

Please sign up or login with your details

Forgot password? Click here to reset