dreamerv3-torch
February 21, 2026 ยท View on GitHub
Important
Notice: Outdated Implementation
This codebase was implemented prior to major updates to DreamerV3 and does not reflect those changes, which accounts for several GitHub Issues in this repository.
An up-to-date and ~5x faster PyTorch DreamerV3 reproduction is now maintained as part of our new repository: r2dreamer. Please refer to that repository for the latest DreamerV3 baseline, provided alongside a PyTorch implementation of R2-Dreamer (ICLR 2026).
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
Method 1: Manual
Get dependencies with python 3.11:
pip install -r requirements.txt
Run training on DMC Vision:
python3 dreamer.py --configs dmc_vision --task dmc_walker_walk --logdir ./logdir/dmc_walker_walk
Monitor results:
tensorboard --logdir ./logdir
To set up Atari or Minecraft environments, please check the scripts located in env/setup_scripts.
Method 2: Docker
Please refer to the Dockerfile for the instructions, as they are included within.
Benchmarks
So far, the following benchmarks can be used for testing.
| Environment | Observation | Action | Budget | Description |
|---|---|---|---|---|
| DMC Proprio | State | Continuous | 500K | DeepMind Control Suite with low-dimensional inputs. |
| DMC Vision | Image | Continuous | 1M | DeepMind Control Suite with high-dimensional images inputs. |
| Atari 100k | Image | Discrete | 400K | 26 Atari games. |
| Crafter | Image | Discrete | 1M | Survival environment to evaluates diverse agent abilities. |
| Minecraft | Image and State | Discrete | 100M | Vast 3D open world. |
| Memory Maze | Image | Discrete | 100M | 3D mazes to evaluate RL agents' long-term memory. |
Results
DMC Proprio
DMC Vision
Atari 100k
Crafter
Troubleshooting
AttributeError: 'NoneType' object has no attribute 'glGetError'
If you encounter this OpenGL-related error when running DMCtasks, it is typically caused by a headless rendering environment setup. Please refer to this discussion/issue for the solution.
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