# Visual Rationalizations in Deep Reinforcement Learning for Atari Games

## TL;DR

This paper introduces a visualization method to explain the decision-making process of deep reinforcement learning agents in Atari games, enhancing transparency and interpretability of their actions.

## Contribution

It proposes a novel visualization approach to generate visual rationalizations for black-box deep RL agents, improving understanding of their decisions.

## Key findings

- Visual rationalizations improve interpretability of RL agents.
- Method applied successfully to Atari game agents.
- Enhances transparency in deep reinforcement learning models.

## Abstract

Due to the capability of deep learning to perform well in high dimensional problems, deep reinforcement learning agents perform well in challenging tasks such as Atari 2600 games. However, clearly explaining why a certain action is taken by the agent can be as important as the decision itself. Deep reinforcement learning models, as other deep learning models, tend to be opaque in their decision-making process. In this work, we propose to make deep reinforcement learning more transparent by visualizing the evidence on which the agent bases its decision. In this work, we emphasize the importance of producing a justification for an observed action, which could be applied to a black-box decision agent.