# Deep Reinforcement Learning Models Predict Visual Responses in the Brain: A Preliminary Result

arXiv: https://arxiv.org/abs/2106.10112 · HTML: https://mlsanity.com/paper/2106.10112/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 27 references that are in the map.
- First posted on arXiv 18 Jun 2021.

## Builds on (most cited first, 7 of 7)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Dueling Network Architectures for Deep Reinforcement Learning](https://mlsanity.com/paper/1511.06581/) (2015)
- [ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning](https://mlsanity.com/paper/1605.02097/) (2016)

## Built on by (most cited first, 2 of 2)

- [A Comprehensive Guide to Explainable AI: From Classical Models to LLMs](https://mlsanity.com/paper/2412.00800/) (2024)
- [What Makes a Face Look like a Hat: Decoupling Low-level and High-level Visual Properties with Image Triplets](https://mlsanity.com/paper/2409.02241/) (2024)

## Abstract (arXiv)

Supervised deep convolutional neural networks (DCNNs) are currently one of the best computational models that can explain how the primate ventral visual stream solves object recognition. However, embodied cognition has not been considered in the existing visual processing models. From the ecological standpoint, humans learn to recognize objects by interacting with them, allowing better classification, specialization, and generalization. Here, we ask if computational models under the embodied learning framework can explain mechanisms underlying object recognition in the primate visual system better than the existing supervised models? To address this question, we use reinforcement learning to train neural network models to play a 3D computer game and we find that these reinforcement learning models achieve neural response prediction accuracy scores in the early visual areas (e.g., V1 and V2) in the levels that are comparable to those accomplished by the supervised neural network model. In contrast, the supervised neural network models yield better neural response predictions in the higher visual areas, compared to the reinforcement learning models. Our preliminary results suggest the future direction of visual neuroscience in which deep reinforcement learning should be included to fill the missing embodiment concept.