https://github.com/facebookresearch/natural_rl_environment

Natural Environment Benchmarks for Reinforcement Learning
https://github.com/facebookresearch/natural_rl_environment

Last synced: 3 months ago
JSON representation

Natural Environment Benchmarks for Reinforcement Learning

• Host: GitHub
• URL: https://github.com/facebookresearch/natural_rl_environment
• Owner: facebookresearch
• License: other
• Archived: true
• Created: 2019-05-09T04:10:31.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2019-05-09T23:46:33.000Z (over 5 years ago)
• Last Synced: 2024-08-02T07:06:57.459Z (6 months ago)
• Language: Python
• Size: 5.22 MB
• Stars: 16
• Watchers: 7
• Forks: 6
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE
  • Code of conduct: CODE_OF_CONDUCT.md

Awesome Lists containing this project

• awesome-deep-rl - Facebook natural_rl_environment - natural signal Atari environments, introduced in the paper Natural Environment Benchmarks for Reinforcement Learning. (Environments)

README

        

This repo contains source code for the natural signal Atari environments, introduced in

the paper [Natural Environment Benchmarks for Reinforcement Learning](https://arxiv.org/abs/1811.06032).



  



## Instructions

1. Install dependencies with `pip install gym[atari] pygame scikit-video opencv-python`

2. Prepare a directory of images or videos

3. Play with new versions of Atari games with the following commands:

```

# Inject gaussian noise to the observations

./natural_env.py --env BreakoutNoFrameskip-v4 --imgsource noise

# Inject some video signals to the observations

./natural_env.py --env SpaceInvadersNoFrameskip-v4 --imgsource videos --resource-files "~/my/videos/*.mp4"

```

## License

This project is under the CC-BY-NC 4.0 license. See [LICENSE](LICENSE) for details.