A set of games designed for testing deep RL agents. This repo contains Python wrappers and an intervention API for Toybox games. Python wrappers for the Atari games are constructed to mock the Arcade Learning Environment and subclass the gym.envs.atari.AtariEnv wrapper. ToyboxBaseEnv may be a good entry point for the gym wrappers.
If you use this code, or otherwise are inspired by our white-box testing approach, please cite our NeurIPS workshop paper:
@inproceedings{foley2018toybox,
title={{Toybox: Better Atari Environments for Testing Reinforcement Learning Agents}},
author={Foley, John and Tosch, Emma and Clary, Kaleigh and Jensen, David},
booktitle={{NeurIPS 2018 Workshop on Systems for ML}},
year={2018}
}
We have a lenghtier paper on ArXiV and can provide a draft of a non-public paper on our acceptance testing framework by request (email at etosch at cs dot umass dot edu).
Watch four minutes of agents playing each game. Both ALE implementations and Toybox implementations have their idiosyncracies, but the core gameplay and concepts have been captured. Pull requests always welcome to improve fidelity.
The rust implementations of the games have moved to a different repository: toybox-rs/toybox-rs
- Create a virtual environment using your python3 installation:
${python} -m venv .env
- If you are on OSX, this is likely
python3
: thus, your command will bepython3 -m venv .env
- If you are not sure of your version, run
python --version
- If you are on OSX, this is likely
- Activate your virtual environment:
source .env/bin/activate
- Install Toybox:
pip install ctoybox
pip install git+https://github.com/toybox-rs/Toybox
- Install requirements: run
pip install -r REQUIREMENTS.txt
- Run
python setup.py install
pip install ctoybox pygame
python -m ctoybox.human_play breakout
python -m ctoybox.human_play amidar
python -m ctoybox.human_play space_invaders
Sample behavioral tests developed with Toybox are frozen and available here. These tests are featured with an OpenAI baselines integration to facilitate off-the-shelf model training.
Tensorflow, OpenAI Gym, OpenCV, and other libraries may or may not break with various Python versions. We have confirmed that the code in this repository will work with the following Python versions:
- 3.6, 3.7
./scripts/utils/start_images --help