Pytorch implementation of Mastering Diverse Domains through World Models. DreamerV3 is a scalable algorithm that outperforms previous approaches across various domains with fixed hyperparameters.

Instructions

Get dependencies:

pip install -r requirements.txt

Train the agent on Walker Walk in DMC Vision:

python3 dreamer.py --configs dmc_vision --task dmc_walker_walk --logdir ./logdir/dmc_walker_walk

Train the agent on Walker Walk in DMC Proprio:

python3 dreamer.py --configs dmc_proprio --task dmc_walker_walk --logdir ./logdir/dmc_walker_walk

Train the agent on Alien in Atari 100K:

python3 dreamer.py --configs atari100k --task atari_alien --logdir ./logdir/atari_alien

Monitor results:

tensorboard --logdir ~/dreamerv3-torch/logdir

Results

More results will be added in the future.

ToDo

Prototyping
Modify implementation details based on the author's implementation
Evaluate on DMC vision
Evaluate on Atari 100K
Add state input capability
Evaluate on DMC Proprio
etc.

Acknowledgments

This code is heavily inspired by the following works:

danijar's Dreamer-v3 jax implementation: https://github.com/danijar/dreamerv3
danijar's Dreamer-v2 tensorflow implementation: https://github.com/danijar/dreamerv2
jsikyoon's Dreamer-v2 pytorch implementation: https://github.com/jsikyoon/dreamer-torch
RajGhugare19's Dreamer-v2 pytorch implementation: https://github.com/RajGhugare19/dreamerv2
denisyarats's DrQ-v2 original implementation: https://github.com/facebookresearch/drqv2