Pytorch implementation of DreamerV2 agent as in Mastering Atari with Discrete World Models, based heavily on the original danijar's Tensorflow 2 implementation. This implementation also follows closely the code structure as the original.
This repo intends to approximate as close as possible the results obtained by the original Tensorflow 2 implementation.
#install pytorch using conda or pip -> follow the instructions here https://pytorch.org
# install ffmpeg for saving agents gifs
# code for Ubuntu/debian
sudo apt install ffmpeg
#install other dependencies
pip3 install -r requirements.txt
python3 dreamerv2/train.py --logdir ~/logdir/atari_pong/dreamerv2/1 --configs defaults atari --task atari_pong
tensorboard --logdir ~/logdir
python dreamerv2/play_test.py --env SpaceInvaders-v0
python dreamerv2/play.py --configs defaults atari --task atari_space_invaders --logdir /logdir/space_invaders_logdir
Features:
Not implemented (converted from original):
Comparison of the Space Invaders Atari game learning performance over our implementation (Pytorch) vs the original implementation (Tensorflow), while using the same hyperparameters.
Results averaged over 5 randomly-seeded runs.
link: https://drive.google.com/drive/folders/1md-5Q5Ewh0a9EwCUb8LcQNSPE6IO8iPb?usp=sharing