# DRLViz: Understanding Decisions and Memory in Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/1909.02982 · HTML: https://mlsanity.com/paper/1909.02982/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2019.

## Built on by (most cited first, 12 of 12)

- [Visual Analytics For Machine Learning: A Data Perspective Survey](https://mlsanity.com/paper/2307.07712/) (2023)
- [An in-depth experimental study of sensor usage and visual reasoning of robots navigating in real environments](https://mlsanity.com/paper/2111.14666/) (2021)
- [Explainability in Deep Reinforcement Learning, a Review into Current Methods and Applications](https://mlsanity.com/paper/2207.01911/) (2022)
- [Interactive Groupwise Comparison for Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2507.04340/) (2025)
- [SIM2REALVIZ: Visualizing the Sim2Real Gap in Robot Ego-Pose Estimation](https://mlsanity.com/paper/2109.11801/) (2021)
- [A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges](https://mlsanity.com/paper/2211.06665/) (2022)
- [AutoDOViz: Human-Centered Automation for Decision Optimization](https://mlsanity.com/paper/2302.09688/) (2023)
- [Are We Closing the Loop Yet? Gaps in the Generalizability of VIS4ML Research](https://mlsanity.com/paper/2308.06290/) (2023)
- [Leveraging Reward Consistency for Interpretable Feature Discovery in Reinforcement Learning](https://mlsanity.com/paper/2309.01458/) (2023)
- [Illuminating LLM Coding Agents: Visual Analytics for Deeper Understanding and Enhancement](https://mlsanity.com/paper/2508.12555/) (2025)
- [Reinforced Labels: Multi-Agent Deep Reinforcement Learning for Point-Feature Label Placement](https://mlsanity.com/paper/2303.01388/) (2023)
- [Abstracted Trajectory Visualization for Explainability in Reinforcement Learning](https://mlsanity.com/paper/2402.07928/) (2024)

## Abstract (arXiv)

We present DRLViz, a visual analytics interface to interpret the internal memory of an agent (e.g. a robot) trained using deep reinforcement learning. This memory is composed of large temporal vectors updated when the agent moves in an environment and is not trivial to understand due to the number of dimensions, dependencies to past vectors, spatial/temporal correlations, and co-correlation between dimensions. It is often referred to as a black box as only inputs (images) and outputs (actions) are intelligible for humans. Using DRLViz, experts are assisted to interpret decisions using memory reduction interactions, and to investigate the role of parts of the memory when errors have been made (e.g. wrong direction). We report on DRLViz applied in the context of video games simulators (ViZDoom) for a navigation scenario with item gathering tasks. We also report on experts evaluation using DRLViz, and applicability of DRLViz to other scenarios and navigation problems beyond simulation games, as well as its contribution to black box models interpretability and explainability in the field of visual analytics.