https://github.com/praveen-palanisamy/webgym

WebGym: Web-browser-based tasks for RL Agents
https://github.com/praveen-palanisamy/webgym

openai-gym reinforcement-learning reinforcement-learning-environments web-rl webgym

Last synced: about 5 hours ago
JSON representation

WebGym: Web-browser-based tasks for RL Agents

• Host: GitHub
• URL: https://github.com/praveen-palanisamy/webgym
• Owner: praveen-palanisamy
• Created: 2021-02-04T04:53:05.000Z (almost 4 years ago)
• Default Branch: main
• Last Pushed: 2021-02-04T06:52:46.000Z (almost 4 years ago)
• Last Synced: 2024-09-16T01:05:13.608Z (2 months ago)
• Topics: openai-gym, reinforcement-learning, reinforcement-learning-environments, web-rl, webgym
• Language: HTML
• Homepage:
• Size: 1.24 MB
• Stars: 12
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
## WebGym

[![PyPI version fury.io](https://badge.fury.io/py/webgym.svg)](https://pypi.python.org/pypi/webgym/)

[![PyPI format](https://img.shields.io/pypi/pyversions/webgym.svg)](https://pypi.python.org/pypi/webgym/)

[![Downloads](https://pepy.tech/badge/webgym)](https://pepy.tech/project/webgym)

The [WebGym](https://github.com/praveen-palanisamy/webgym) package provides learning environments for agents to perceive the world-wide-web like how we (humans) perceive – using the pixels rendered on to the display screen. The agent interacts with the environment using keyboard and mouse events as actions. This allows the agent to experience the world-wide-web like how we do thereby require no new additional modifications for the agents to train. This allows us to train RL agents that can directly work with the web-based pages and applications to complete real-world tasks. It is an extension of Wolrd-Of-Bits (WOB) & MiniWoB++.

WebGym is part of [TensorFlow Reinforcement Learning Cookbook](https://github.com/PacktPublishing/Tensorflow-2-Reinforcement-Learning-Cookbook). More details about this package, see Deep RL Web Assistants discussed in **Chapter 6 - RL in real-world: Building intelligent agents to complete your To-dos**