# Visual Rationalizations in Deep Reinforcement Learning for Atari Games

arXiv: https://arxiv.org/abs/1902.00566 · HTML: https://mlsanity.com/paper/1902.00566/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Feb 2019.

## Built on by (most cited first, 8 of 8)

- [A Survey of Explainable Reinforcement Learning](https://mlsanity.com/paper/2202.08434/) (2022)
- [Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents](https://mlsanity.com/paper/2401.05821/) (2024)
- [A Survey of State Representation Learning for Deep Reinforcement Learning](https://mlsanity.com/paper/2506.17518/) (2025)
- [Hindsight PRIORs for Reward Learning from Human Preferences](https://mlsanity.com/paper/2404.08828/) (2024)
- [Feature-Based Interpretable Reinforcement Learning based on State-Transition Models](https://mlsanity.com/paper/2105.07099/) (2021)
- [Action Q-Transformer: Visual Explanation in Deep Reinforcement Learning with Encoder-Decoder Model using Action Query](https://mlsanity.com/paper/2306.13879/) (2023)
- [Revealing the Learning Process in Reinforcement Learning Agents Through Attention-Oriented Metrics](https://mlsanity.com/paper/2406.14324/) (2024)
- [Attention Trajectories as a Diagnostic Axis for Deep Reinforcement Learning](https://mlsanity.com/paper/2511.20591/) (2025)

## Abstract (arXiv)

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.