The Atari Data Scraper
This addresses the lack of trust and understanding in reinforcement learning for researchers and practitioners, but it is incremental as it builds on existing methods without major breakthroughs.
The paper tackles the problem of deep reinforcement learning agents being black boxes by introducing the Atari Data Scraper library, which collects data to help interpret and understand these agents, though no concrete performance numbers are provided.
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