The Atari Data Scraper

TL;DR

This paper introduces the Atari Data Scraper, a tool that collects data from deep reinforcement learning agents playing Atari games to improve understanding and interpretability of these black-box models.

Contribution

The paper presents a novel data collection library that enables analysis and interpretation of deep reinforcement learning agents in Atari environments.

Findings

Data collected helps interpret agent decision-making.

Improves transparency of deep reinforcement learning models.

Facilitates trust and understanding in RL algorithms.

Abstract

Reinforcement learning has made great strides in recent years due to the success of methods using deep neural networks. However, such neural networks act as a black box, obscuring the inner workings. While reinforcement learning has the potential to solve unique problems, a lack of trust and understanding of reinforcement learning algorithms could prevent their widespread adoption. Here, we present a library that attaches a "data scraper" to deep reinforcement learning agents, acting as an observer, and then show how the data collected by the Atari Data Scraper can be used to understand and interpret deep reinforcement learning agents. The code for the Atari Data Scraper can be found here: https://github.com/IRLL/Atari-Data-Scraper