https://github.com/sisl/pyrorl

An RL environment made for wildfire evacuation.
https://github.com/sisl/pyrorl

Last synced: 9 months ago
JSON representation

An RL environment made for wildfire evacuation.

• Host: GitHub
• URL: https://github.com/sisl/pyrorl
• Owner: sisl
• License: mit
• Created: 2023-07-13T02:50:32.000Z (almost 3 years ago)
• Default Branch: master
• Last Pushed: 2025-04-02T05:38:01.000Z (about 1 year ago)
• Last Synced: 2025-09-05T22:46:02.752Z (10 months ago)
• Language: Python
• Homepage: https://sisl.github.io/PyroRL/
• Size: 4.6 MB
• Stars: 18
• Watchers: 2
• Forks: 0
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Codeowners: CODEOWNERS

Awesome Lists containing this project

README

          

██████╗ ██╗   ██╗██████╗  ██████╗ ██████╗ ██╗     

██╔══██╗╚██╗ ██╔╝██╔══██╗██╔═══██╗██╔══██╗██║     

██████╔╝ ╚████╔╝ ██████╔╝██║   ██║██████╔╝██║     

██╔═══╝   ╚██╔╝  ██╔══██╗██║   ██║██╔══██╗██║     

██║        ██║   ██║  ██║╚██████╔╝██║  ██║███████╗

╚═╝        ╚═╝   ╚═╝  ╚═╝ ╚═════╝ ╚═╝  ╚═╝╚══════╝



![example workflow](https://github.com/sisl/PyroRL/actions/workflows/testing.yml/badge.svg) [![codecov](https://codecov.io/github/sisl/PyroRL/graph/badge.svg?token=wBlFGsd5sS)](https://codecov.io/github/sisl/PyroRL) [![](https://img.shields.io/badge/docs-latest-blue.svg)](https://sisl.github.io/PyroRL/)  [![DOI](https://joss.theoj.org/papers/10.21105/joss.06739/status.svg)](https://joss.theoj.org/papers/10.21105/joss.06739)

PyroRL is a new reinforcement learning environment built for the simulation of wildfire evacuation. Check out the [docs](https://sisl.github.io/PyroRL/) and the [demo](https://www.youtube.com/embed/Pt4cI5jBbKo).

## How to Use

First, install our package. Note that PyroRL requires Python version 3.8:

```bash

pip install pyrorl

```

To use our wildfire evacuation environment, define the dimensions of your grid, where the populated areas are, the paths, and which populated areas can use which path. See an example below.

```python

# Create environment

kwargs = {

    'num_rows': num_rows,

    'num_cols': num_cols,

    'populated_areas': populated_areas,

    'paths': paths,

    'paths_to_pops': paths_to_pops

}

env = gymnasium.make('pyrorl/PyroRL-v0', **kwargs)

# Run a simple loop of the environment

env.reset()

for _ in range(10):

    # Take action and observation

    action = env.action_space.sample()

    observation, reward, terminated, truncated, info = env.step(action)

    # Render environment and print reward

    env.render()

    print("Reward: " + str(reward))

```

A compiled visualization of numerous iterations is seen below. For more examples, check out the `examples/` folder.

![Example Visualization of PyroRL](imgs/example_visualization.gif)

For a more comprehensive tutorial, check out the [quickstart](https://sisl.github.io/PyroRL/quickstart/) page on our docs website.

## How to Contribute

For information on how to contribute, check out our [contribution guide](https://sisl.github.io/PyroRL/contribution-guide/).