Skip to content
BabyAI platform. A testbed for training agents to understand and execute language commands.
Branch: master
Clone or download
dyth and maximecb Values returned from max and sample now same shape (#73)
* Values returned from max and sample now same shape

* Update
Latest commit 76ea387 Jun 13, 2019
Type Name Latest commit message Commit time
Failed to load latest commit information.
babyai Values returned from max and sample now same shape (#73) Jun 13, 2019
docs Only mention docker image in ICLR19 branch. (#70) May 2, 2019
media Added screenshot functionality to, screenshots Oct 9, 2018
.gitignore ignore locally trained information Jan 30, 2019
.travis.yml Fixing error due to removed pip option on (#51) Feb 23, 2019 Separate README into sections, added table of contents (#68) Apr 30, 2019
Dockerfile Small fixes to Dockerfile. Improve comments. (#64) Apr 5, 2019
LICENSE Initial commit Oct 19, 2017 Only mention docker image in ICLR19 branch. (#70) May 2, 2019
environment.yaml change yaml and readme Jan 31, 2019 Revert "few improvements to bot advisor" Dec 14, 2018 Fixing error due to removed pip option on (#51) Feb 23, 2019

BabyAI Platform

Build Status

A platform for simulating language learning with a human in the loop. This is an ongoing research project based at Mila.



If you use this platform in your research, please cite:

  title={Baby{AI}: First Steps Towards Grounded Language Learning With a Human In the Loop},
  author={Maxime Chevalier-Boisvert and Dzmitry Bahdanau and Salem Lahlou and Lucas Willems and Chitwan Saharia and Thien Huu Nguyen and Yoshua Bengio},
  booktitle={International Conference on Learning Representations},

Replicating ICLR19 Results

The master branch of this repository is updated frequently. If you are looking to replicate or compare against the results from the ICLR19 BabyAI paper, please use the docker image, demonstration dataset and source code from the iclr19 branch of this repository.



  • Python 3.5+
  • OpenAI Gym
  • NumPy
  • PyQT5
  • PyTorch 0.4.1+

Start by manually installing PyTorch. See the PyTorch website for installation instructions specific to your platform.

Then, clone this repository and install the other dependencies with pip3:

git clone
cd babyai
pip3 install --editable .

Installation using Conda (Alternative Method)

If you are using conda, you can create a babyai environment with all the dependencies by running:

git clone
cd babyai
conda env create -f environment.yaml
source activate babyai

After that, execute the following commands to setup the environment.

cd ..
git clone
cd gym-minigrid
pip install --editable .

The last command installs the repository in editable mode. Move back to the babyai repository and install that in editable mode as well.

cd ../babyai
pip install --editable .

BabyAI Storage Path

Add this line to .bashrc (Linux), or .bash_profile (Mac).


where /<PATH>/<TO>/<BABYAI>/<REPOSITORY>/<PARENT> is the folder where you typed git clone earlier.

Models, logs and demos will be produced in this directory, in the folders models, logs and demos respectively.


To run the interactive GUI application that illustrates the platform:


The level being run can be selected with the --env option, eg:

scripts/ --env BabyAI-UnlockPickup-v0

The Levels

Documentation for the ICLR19 levels can be found in docs/ There are also older levels documented in docs/

About this Project

BabyAI is an open-ended grounded language acquisition effort at Mila. The current BabyAI platform was designed to study data-effiency of existing methods under the assumption that a human provides all teaching signals (i.e. demonstrations, rewards, etc.). For more information, see the ICLR19 paper.

You can’t perform that action at this time.