# Machine versus Human Attention in Deep Reinforcement Learning Tasks

arXiv: https://arxiv.org/abs/2010.15942 · HTML: https://mlsanity.com/paper/2010.15942/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Oct 2020.

## Built on by (most cited first, 16 of 16)

- [A Survey on Vision-Language-Action Models for Embodied AI](https://mlsanity.com/paper/2405.14093/) (2024)
- [A Survey On Enhancing Reinforcement Learning in Complex Environments: Insights from Human and LLM Feedback](https://mlsanity.com/paper/2411.13410/) (2024)
- [Explainability in Deep Reinforcement Learning, a Review into Current Methods and Applications](https://mlsanity.com/paper/2207.01911/) (2022)
- [Using Human Perception to Regularize Transfer Learning](https://mlsanity.com/paper/2211.07885/) (2022)
- [Imitation Learning with Human Eye Gaze via Multi-Objective Prediction](https://mlsanity.com/paper/2102.13008/) (2021)
- [Human-AI Shared Control via Policy Dissection](https://mlsanity.com/paper/2206.00152/) (2022)
- [Gaze-Guided Learning: Avoiding Shortcut Bias in Visual Classification](https://mlsanity.com/paper/2504.05583/) (2025)
- [A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges](https://mlsanity.com/paper/2211.06665/) (2022)
- [AEGIS: Human Attention-based Explainable Guidance for Intelligent Vehicle Systems](https://mlsanity.com/paper/2504.05950/) (2025)
- [Revealing Human Attention Patterns from Gameplay Analysis for Reinforcement Learning](https://mlsanity.com/paper/2504.11118/) (2025)
- [Explainable reinforcement learning from human feedback to improve alignment](https://mlsanity.com/paper/2512.13837/) (2025)
- [Active Vision Reinforcement Learning under Limited Visual Observability](https://mlsanity.com/paper/2306.00975/) (2023)
- [Revealing the Learning Process in Reinforcement Learning Agents Through Attention-Oriented Metrics](https://mlsanity.com/paper/2406.14324/) (2024)
- [A modular framework for automated evaluation of procedural content generation in serious games with deep reinforcement learning agents](https://mlsanity.com/paper/2505.16801/) (2025)
- [Attention Trajectories as a Diagnostic Axis for Deep Reinforcement Learning](https://mlsanity.com/paper/2511.20591/) (2025)
- [Estimating Central, Peripheral, and Temporal Visual Contributions to Human Decision Making in Atari Games](https://mlsanity.com/paper/2604.04439/) (2026)

## Abstract (arXiv)

Deep reinforcement learning (RL) algorithms are powerful tools for solving visuomotor decision tasks. However, the trained models are often difficult to interpret, because they are represented as end-to-end deep neural networks. In this paper, we shed light on the inner workings of such trained models by analyzing the pixels that they attend to during task execution, and comparing them with the pixels attended to by humans executing the same tasks. To this end, we investigate the following two questions that, to the best of our knowledge, have not been previously studied. 1) How similar are the visual representations learned by RL agents and humans when performing the same task? and, 2) How do similarities and differences in these learned representations explain RL agents' performance on these tasks? Specifically, we compare the saliency maps of RL agents against visual attention models of human experts when learning to play Atari games. Further, we analyze how hyperparameters of the deep RL algorithm affect the learned representations and saliency maps of the trained agents. The insights provided have the potential to inform novel algorithms for closing the performance gap between human experts and RL agents.