# EAR

**Repository Path**: xinci/EAR

## Basic Information

- **Project Name**: EAR
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2024-04-11
- **Last Updated**: 2024-04-11

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Environment Agnostic Representation for Visual Reinforcement learning (ICCV23)
<img src="./img/method.png" width="50%" height="50%">
This is an official Pytorch implementation of the paper [Environment Agnostic Representation for Visual Reinforcement learning].(https://openaccess.thecvf.com/content/ICCV2023/papers/Choi_Environment_Agnostic_Representation_for_Visual_Reinforcement_Learning_ICCV_2023_paper.pdf):

```
@inproceedings{choi2023environment,
  title={Environment Agnostic Representation for Visual Reinforcement Learning},
  author={Choi, Hyesong and Lee, Hunsang and Jeong, Seongwon and Min, Dongbo},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={263--273},
  year={2023}
}
```

Our implementation is based on [SAC](https://github.com/denisyarats/pytorch_sac_ae), [PAD](https://github.com/nicklashansen/policy-adaptation-during-deployment), and [DM Control Suite](https://github.com/google-deepmind/dm_control).