TextWorld

A text-based game generator and extensible sandbox learning environment for training and testing reinforcement learning (RL) agents. Also check out aka.ms/textworld for more info about TextWorld and its creators. Have questions or feedback about TextWorld? Send them to [email protected] or use the Gitter channel listed above.

Installation

TextWorld supports Python 3.9/3.10/3.11/3.12 for Linux and macOS systems only at the moment. For Windows users, docker can be used as a workaround (see Docker section below).

Requirements

TextWorld requires some system libraries for its native components. On a Debian/Ubuntu-based system, these can be installed with

sudo apt update && sudo apt install build-essential libffi-dev python3-dev curl git

And on macOS, with

brew install libffi curl git

Note: We advise our users to use virtual environments to avoid Python packages from different projects to interfere with each other. Popular choices are Conda Environments and Virtualenv

Installing TextWorld

The easiest way to install TextWorld is via pip:

pip install textworld

Or, after cloning the repo, go inside the root folder of the project (i.e. alongside setup.py) and run

pip install .

Visualization

TextWorld comes with some tools to visualize game states. Make sure all dependencies are installed by running

pip install textworld[vis]

Then, you will need to install either the Chrome or Firefox webdriver (depending on which browser you have currently installed). If you have Chrome already installed you can use the following command to install chromedriver

pip install chromedriver_installer

Current visualization tools include: take_screenshot, visualize and show_graph from textworld.render.

Docker

A docker container with the latest TextWorld release is available on DockerHub.

docker pull marccote19/textworld
docker run -p 8888:8888 -it --rm marccote19/textworld

Then, in your browser, navigate to the Jupyter notebook's link displayed in your terminal. The link should look like this

http://127.0.0.1:8888/?token=8d7aaa...e95

Note: See README.md in the docker folder for troubleshooting information.

Usage

Generating a game

TextWorld provides an easy way of generating simple text-based games via the tw-make script. For instance,

tw-make custom --world-size 5 --nb-objects 10 --quest-length 5 --seed 1234 --output tw_games/custom_game.z8

where custom indicates we want to customize the game using the following options: --world-size controls the number of rooms in the world, --nb-objects controls the number of objects that can be interacted with (excluding doors) and --quest-length controls the minimum number of commands that is required to type in order to win the game. Once done, the game custom_game.z8 will be saved in the tw_games/ folder.

Playing a game (terminal)

To play a game, one can use the tw-play script. For instance, the command to play the game generated in the previous section would be

tw-play tw_games/custom_game.z8

Note: Only Z-machine's games (*.z1 through *.z8) are supported.

To visualize the game state while playing, use the --viewer [port] option.

tw-play tw_games/custom_game.z8 --viewer

A new browser tab should open and track your progress in the game.

Playing a game (Python + Gym-like API)

Here's how you can interact with a text-based game from within Python using a Gym-like API.

import textworld.gym

# Register a text-based game as a new environment.
env_id = textworld.gym.register_game("tw_games/custom_game.z8",
                                     max_episode_steps=50)

env = textworld.gym.make(env_id)  # Start the environment.

obs, infos = env.reset()  # Start new episode.
env.render()

score, moves, done = 0, 0, False
while not done:
    command = input("> ")
    obs, score, done, infos = env.step(command)
    env.render()
    moves += 1

env.close()
print("moves: {}; score: {}".format(moves, score))

Note: To play text-based games without a Gym-like API, see Playing text-based games with TextWorld.ipynb

Documentation

For more information about TextWorld, check the documentation.

Visual Studio Code

You can install the textworld-vscode extension that enables syntax highlighting for editing .twl and .twg TextWorld files.

Notebooks

Check the notebooks provided with the framework to see what you can do with it. You will need the Jupyter Notebook to run them. You can install it with

pip install jupyter

여기까지가 README 앞부분입니다. 나머지는 원문에서 읽을 수 있습니다. README 전문 보기 ↗