Skip to main content

BrowserGym: a gym environment for web task automation in the Chromium browser

Project description

BrowserGym

This package provides browsergym, a gym environment for web task automation in the Chromium browser.

Setup

  1. Install the package
pip install browsergym
  1. Install playwright browsers
playwright install
  1. For each benchmark, specific setup instructions must be followed

Usage

Open-ended task example

Boilerplate code to run an agent on the openended task:

import gymnasium as gym
import browsergym.core  # register openended taskj as a gym environment

env = gym.make(
    "browsergym/openended", start_url="https://www.google.com/", wait_for_user_message=True
)
obs, info = env.reset()
done = False
while not done:
    action = ...  # implement your agent here
    obs, reward, terminated, truncated, info = env.step(action)

MiniWoB++ task example

Boilerplate code to run an agent on a miniwob task:

import gymnasium as gym
import browsergym.miniwob  # register miniwob tasks as gym environments

env = gym.make("browsergym/miniwob.choose-list")
obs, info = env.reset()
done = False
while not done:
    action = ...  # implement your agent here
    obs, reward, terminated, truncated, info = env.step(action)

WebArena task example

Boilerplate code to run an agent on a webarena task:

import gymnasium as gym
import browsergym.webarena  # register webarena tasks as gym environments

env = gym.make("browsergym/webarena.310")
obs, info = env.reset()
done = False
while not done:
    action = ...  # implement your agent here
    obs, reward, terminated, truncated, info = env.step(action)

WorkArena task example

Boilerplate code to run an agent on a workarena task:

import gymnasium as gym
import browsergym.workarena  # register workarena tasks as gym environments

env = gym.make("browsergym/workarena.servicenow.order-ipad-pro")
obs, info = env.reset()
done = False
while not done:
    action = ...  # implement your agent here
    obs, reward, terminated, truncated, info = env.step(action)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

browsergym-0.0.1a10.tar.gz (2.7 kB view details)

Uploaded Source

Built Distribution

browsergym-0.0.1a10-py3-none-any.whl (2.5 kB view details)

Uploaded Python 3

File details

Details for the file browsergym-0.0.1a10.tar.gz.

File metadata

  • Download URL: browsergym-0.0.1a10.tar.gz
  • Upload date:
  • Size: 2.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/5.0.0 CPython/3.12.2

File hashes

Hashes for browsergym-0.0.1a10.tar.gz
Algorithm Hash digest
SHA256 18f1588e41f0e1dd9194db17a1663d4eeb04298e4fa7d64ffd9e66d5852d0b91
MD5 adb2d0789b20aad8088aeb52a5a5cc58
BLAKE2b-256 e895a1dd1f7bf14f15b667f1fc6d0a448842c537f5b5f09f1e576bf287cb6aa7

See more details on using hashes here.

File details

Details for the file browsergym-0.0.1a10-py3-none-any.whl.

File metadata

File hashes

Hashes for browsergym-0.0.1a10-py3-none-any.whl
Algorithm Hash digest
SHA256 03c88ed3cdcbca78f23ba19899d41785feae77981f7ede6eddca7158060934e7
MD5 5d0cc7e23ca84d7dd5359925b56db2bf
BLAKE2b-256 4e5584af035be0be3ecaf60f2d26006560cf7e68bd2d869726e79a4c49f6915f

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page