- Install the dependencies with
pip install requirements.txt
- Run all experiments with
python3 tmux-runs.py
- To test: python3 main.py --env="acrobot" --agent="rainbow" --initial_seed="1" --exp="clip_rewards"
In this work we argue ...
To use the algorithms proposed in the Revisiting Rainbow paper, you need python3 installed, make sure pip is also up to date. If you want to run the MinAtar experiments you should install it. To install MinAtar, please check the following paper (Young et al., 2019) and repository (github):
- Clone the repo:
https://github.com/JohanSamir/revisiting_rainbow
If you prefer running the algorithms in a virtualenv, you can do the following before step 2:
python3 -m venv venv
source venv/bin/activate
# Upgrade Pip
pip install --upgrade pip
- Finally setup the environment and install Revisiting Rainbow's dependencies
pip install -U pip
pip install -r revisiting_rainbow/requirements.txt
If you use Revisiting Rainbow in your research please cite the following:
Johan S. Obando Ceron, & Pablo Samuel Castro (2020). Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research. In Deep Reinforcement Learning Workshop, NeurIPS 2020. arXiv preprint:
In BibTeX format:
@inproceedings{obando20revisiting,
author = {Johan S. Obando Ceron and Pablo Samuel Castro},
title = {Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research},
booktitle = {Deep Reinforcement Learning Workshop, NeurIPS 2020},
year = 2020
}