Metadata-Version: 2.4
Name: brawlgym
Version: 0.1.3
Summary: A python API that can be used to treat the game Brawlhalla as an OpenAI Gym-like environment for Reinforcement Learning projects.
Home-page: https://github.com/brawlgym/brawlgym
Author: chrisrca
License: Apache 2.0
Keywords: brawlhalla,gym,reinforcement-learning
Classifier: Development Status :: 3 - Alpha
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Operating System :: Microsoft :: Windows
Requires-Python: ==3.11.*
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy>=1.19
Requires-Dist: py7zr>=0.20
Requires-Dist: pycaw>=20220416
Dynamic: author
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: keywords
Dynamic: license
Dynamic: license-file
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# The Brawlhalla Gym

This is a python API that can be used to treat the game [Brawlhalla](https://www.brawlhalla.com) as
though it were an [OpenAI Gym](https://gym.openai.com)-style environment for Reinforcement Learning
projects. It is heavily inspired by [RLGym](https://rlgym.org/), and the component model will be
familiar if you have used it.

[<video src="https://github.com/user-attachments/assets/a7d81157-f03d-47d8-91f1-5a2bf6a597ef" controls autoplay loop muted playsinline></video>](https://github.com/user-attachments/assets/27544553-7e9a-4d42-8879-c73efd1a8125)

## Requirements
* A Windows 10 or 11 PC
* Brawlhalla (Steam)
* Python 3.9 or newer

## Installation
Install the library via pip:
```
pip install brawlgym
```

## Usage
Wiki coming soon... Check out [brawlgym-ppo](https://github.com/brawlgym/brawlgym-ppo) in the meantime!
