Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/real-stanford/aspire
[NeurIPS 2022] ASPiRe: Adaptive Skill Priors for Reinforcement Learning
https://github.com/real-stanford/aspire
Last synced: 2 days ago
JSON representation
[NeurIPS 2022] ASPiRe: Adaptive Skill Priors for Reinforcement Learning
- Host: GitHub
- URL: https://github.com/real-stanford/aspire
- Owner: real-stanford
- License: mit
- Created: 2022-09-22T22:29:36.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2022-10-19T14:39:19.000Z (about 2 years ago)
- Last Synced: 2023-09-29T00:22:19.300Z (about 1 year ago)
- Language: Python
- Homepage:
- Size: 36.1 KB
- Stars: 10
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ASPiRe
[Mengda Xu](https://www.cs.columbia.edu/~shurans/)
[Manuela Veloso](http://www.cs.cmu.edu/~mmv/)
[Shuran Song](https://www.cs.columbia.edu/~shurans/)
Columbia University
Neural Information Processing Systems / NeurIPS 2022
### [Project Page](https://aspire.cs.columbia.edu//)
## Overview
This repo contains the PyTorch implementation for paper "ASPiRe: Adaptive Skill Priors for Reinforcement Learning".
## Content
- [Installation](#installation)
- [Data Preparation](#data-preparation)
- [Training](#training)
## Installation
```sh
cd path/to/ASPiRe
conda env create -f environment.yml
source activate aspire
pip install -e .
```
## Data Preparation
We provide the data for learning the skill priors for point maze.
- [navigation_dataset](https://drive.google.com/file/d/1sbAWwca32OQwpa1WxGLhrH3gRl4Cc-hx/view?usp=sharing): The point mass agent navigates in medium size mazes.
- [avoid_dataset](https://drive.google.com/file/d/1O-HFBwzSk-sd46-PF08O49mtww5wCuZM/view?usp=sharing): The point mass agent avoids the obstacale in front.
## Training
Learning skill priors
```sh
python script/train_prior.py --d1 NAV_DATA_PATH --d2 AVOID_DATA_PATH --log --kl_analytic --use_batch_norm --name PRIOR_NAME
```
A directory will be created at `skill_prior/maze/PRIOR_NAME`, in which checkpoints will be stored.
Learning downstrem task
```sh
python script/train_maze.py --prior_name PRIOR_NAME --prior_checkpoint PRIOR_CHECKPOINT --analytic_kl --raw_kl --use_batch_norm --weight_use_batch_norm --name EXP_NAME
```
A directory will be created at `Experiment/EXP_NAME`, in which checkpoints will be stored.
## BibTeX
```
@inproceedings{
anonymous2022aspire,
title={{ASP}iRe: Adaptive Skill Priors for Reinforcement Learning},
author={Anonymous},
booktitle={Thirty-Sixth Conference on Neural Information Processing Systems},
year={2022},
url={https://openreview.net/forum?id=sr0289wAUa}
}
```
## License
This repository is released under the MIT license. See [LICENSE](LICENSE) for additional details.
## Acknowledgement