# Divergent representations of ethological visual inputs emerge from supervised, unsupervised, and reinforcement learning

arXiv: https://arxiv.org/abs/2112.02027 · HTML: https://mlsanity.com/paper/2112.02027/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 46 references that are in the map.
- First posted on arXiv 3 Dec 2021.

## Builds on (most cited first, 14 of 14)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [Reinforcement Learning with Unsupervised Auxiliary Tasks](https://mlsanity.com/paper/1611.05397/) (2016)
- [dm_control: Software and Tasks for Continuous Control](https://mlsanity.com/paper/2006.12983/) (2020)
- [Data-Efficient Reinforcement Learning with Self-Predictive Representations](https://mlsanity.com/paper/2007.05929/) (2020)
- [Decoupling Representation Learning from Reinforcement Learning](https://mlsanity.com/paper/2009.08319/) (2020)
- [Representation Matters: Offline Pretraining for Sequential Decision Making](https://mlsanity.com/paper/2102.05815/) (2021)
- [Unsupervised Predictive Memory in a Goal-Directed Agent](https://mlsanity.com/paper/1803.10760/) (2018)
- [Environmental drivers of systematicity and generalization in a situated agent](https://mlsanity.com/paper/1910.00571/) (2019)
- [Neural tuning and representational geometry](https://mlsanity.com/paper/2104.09743/) (2021)
- [Interpreting neural computations by examining intrinsic and embedding dimensionality of neural activity](https://mlsanity.com/paper/2107.04084/) (2021)
- [Deep neuroethology of a virtual rodent](https://mlsanity.com/paper/1911.09451/) (2019)

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

- [Causes and Consequences of Representational Similarity in Machine Learning Models](https://mlsanity.com/paper/2505.13899/) (2025)
- [A novel feature-scrambling approach reveals the capacity of convolutional neural networks to learn spatial relations](https://mlsanity.com/paper/2212.06021/) (2022)

## Abstract (arXiv)

Artificial neural systems trained using reinforcement, supervised, and unsupervised learning all acquire internal representations of high dimensional input. To what extent these representations depend on the different learning objectives is largely unknown. Here we compare the representations learned by eight different convolutional neural networks, each with identical ResNet architectures and trained on the same family of egocentric images, but embedded within different learning systems. Specifically, the representations are trained to guide action in a compound reinforcement learning task; to predict one or a combination of three task-related targets with supervision; or using one of three different unsupervised objectives. Using representational similarity analysis, we find that the network trained with reinforcement learning differs most from the other networks. Using metrics inspired by the neuroscience literature, we find that the model trained with reinforcement learning has a sparse and high-dimensional representation wherein individual images are represented with very different patterns of neural activity. Further analysis suggests these representations may arise in order to guide long-term behavior and goal-seeking in the RL agent. Finally, we compare the representations learned by the RL agent to neural activity from mouse visual cortex and find it to perform as well or better than other models. Our results provide insights into how the properties of neural representations are influenced by objective functions and can inform transfer learning approaches.