Deep Reinforcement Learning Environments for web-based tasks using Playwright
Project description
PlaywrightGym - Train RL Agents for Web tasks
Web-Browser-based learning environments for Deep Reinforcement Learning.
Usage
import gym
import playwrightgym
env = gym.make("LoginFormVisual-v0")
Examples
- examples/demonstrator.py: Starter class to get human/manual demonstrations
- examples/gather_demonstrations.py: Starter script to gather human/manual demonstrations and store in RLLib-compatible file format for offline RL
Dev Setup
- Install python-poetry:
curl -sSL https://raw.githubusercontent.com/python-poetry/poetry/master/get-poetry.py | python -
- Clone and
cd
to this projects:git clone https://github.com/praveen-palanisamy/playwrightgym && cd playwrightgym
- Activate python venv:
poetry shell
- Install dependencies and
playwrightgym
in editable mode:poetry install
- Install browsers for playwright:
playwright install
- Ready!
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
playwrightgym-0.1.0.tar.gz
(8.8 kB
view hashes)
Built Distribution
Close
Hashes for playwrightgym-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | c2d1f51810c61b283d0dbcee63d8d68e4110700d7872785c5664a31590b86e9c |
|
MD5 | 5026aa562ab4571c66fa7a5ca2698f48 |
|
BLAKE2b-256 | 1beb26748272194fb538cd6414792e839296ed9a3d7521629f9e4868e2d33acf |