Metadata-Version: 2.3
Name: browsergym-miniwob
Version: 0.1.0rc6
Summary: MiniWoB++ benchmark for BrowserGym
Project-URL: homepage, https://github.com/ServiceNow/BrowserGym
Author: Rim Assouel, Maxime Gasse, Tom Marty
License: Apache-2.0
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >3.7
Requires-Dist: browsergym-core==0.1.0rc6
Description-Content-Type: text/markdown

# Miniwob benchmark for BrowserGym

This package provides `browsergym.miniwob`, which is an unofficial port of the [MiniWoB++](https://miniwob.farama.org/) benchmark for BrowserGym.

## Setup

1. Install the package
```sh
pip install browsergym-miniwob
```

2. Clone miniwob (use a specific frozen commit for reproducibility)
```sh
git clone git@github.com:Farama-Foundation/miniwob-plusplus.git
git -C "./miniwob-plusplus" reset --hard 7fd85d71a4b60325c6585396ec4f48377d049838
```

3. Setup Miniwob URL (change `PATH_TO_MINIWOB_CLONED_REPO` here to the absolute path to your `miniwob-plusplus` folder)
```sh
export MINIWOB_URL="file://<PATH_TO_MINIWOB_CLONED_REPO>/miniwob/html/miniwob/"
```

Alternatively, one can [setup a simple HTTP server](https://miniwob.farama.org/content/viewing/) and use a proper URL.
