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

01/18/2021
by   Tobias Huber, et al.
0

Recent years saw a plethora of work on explaining complex intelligent agents. One example is the development of several algorithms that generate saliency maps which show how much each pixel attributed to the agents' decision. However, most evaluations of such saliency maps focus on image classification tasks. As far as we know, there is no work which thoroughly compares different saliency maps for Deep Reinforcement Learning agents. This paper compares four perturbation-based approaches to create saliency maps for Deep Reinforcement Learning agents trained on four different Atari 2600 games. All four approaches work by perturbing parts of the input and measuring how much this affects the agent's output. The approaches are compared using three computational metrics: dependence on the learned parameters of the agent (sanity checks), faithfulness to the agent's reasoning (input degradation), and run-time.

READ FULL TEXT

page 3

page 4

research
12/23/2019

Explain Your Move: Understanding Agent Actions Using Focused Feature Saliency

As deep reinforcement learning (RL) is applied to more tasks, there is a...
research
08/07/2019

Free-Lunch Saliency via Attention in Atari Agents

We propose a new approach to visualize saliency maps for deep neural net...
research
12/09/2019

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

Saliency maps have been used to support explanations of deep reinforceme...
research
10/29/2020

Human versus Machine Attention in Deep Reinforcement Learning Tasks

Deep reinforcement learning (RL) algorithms are powerful tools for solvi...
research
10/31/2017

Visualizing and Understanding Atari Agents

Deep reinforcement learning (deep RL) agents have achieved remarkable su...
research
11/27/2018

Quality-Aware Multimodal Saliency Detection via Deep Reinforcement Learning

Incorporating various modes of information into the machine learning pro...
research
06/15/2023

Inroads into Autonomous Network Defence using Explained Reinforcement Learning

Computer network defence is a complicated task that has necessitated a h...

Please sign up or login with your details

Forgot password? Click here to reset