AI Rank
中文
← Open Source
NM512

dreamerv3-torch

Implementation of Dreamer v3 in pytorch.

Model DevelopmentReinforcement LearningPython
Open on GitHub
Momentum
+-1stars in 24 hours-0.1%
888
Stars
219
Forks
+-1
This week
6
Contributors
Created 2023-02-11 · Updated 2026-10-15 · #19031 today
Top developers
NM512ktolnoszdx3578

NM512/dreamerv3-torch is ranked 19,031 with 888 stars.

Same-category comparison

NM512/dreamerv3-torch is ranked 19,031 among these 8 peers; maxjcohen/transformer is ranked 19,025.

Same-category comparison
NameRankMetrics
cszn/USRNet19,018
Language:
Python
Stars:
919
Forks:
120
Description:
Deep Unfolding Network for Image Super-Resolution (CVPR, 2020) (PyTorch).
EvelynFan/FaceFormer19,019
Language:
Python
Stars:
917
Forks:
148
Description:
[CVPR 2022] FaceFormer: Speech-Driven 3D Facial Animation with Transformers.
lucidrains/muse-maskgit-pytorch19,021
Language:
Python
Stars:
916
Forks:
87
Description:
Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch.
maxjcohen/transformer19,025
Language:
Jupyter Notebook
Stars:
903
Forks:
166
Description:
Implementation of Transformer model (originally from Attention is All You Need) applied to Time Series.
YBYBZhang/ControlVideo19,045
Language:
Python
Stars:
861
Forks:
60
Description:
[ICLR 2024] Official pytorch implementation of "ControlVideo: Training-free Controllable Text-to-Video Generation".
hank-ai/darknet19,046
Language:
C++
Stars:
859
Forks:
113
Description:
Darknet/YOLO object detection framework.
Chengsong-Huang/R-Zero19,048
Language:
Python
Stars:
857
Forks:
77
Description:
[ICLR2026] codes for R-Zero: Self-Evolving Reasoning LLM from Zero Data (https://www.arxiv.org/pdf/2508.05004).
devendrachaplot/Neural-SLAM19,050
Language:
Python
Stars:
852
Forks:
153
Description:
Pytorch code for ICLR-20 Paper "Learning to Explore using Active Neural SLAM".
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguagePython
CategoryModel Development
SubcategoryReinforcement Learning
KeywordsRL
Stars888
Forks219
Contributors6
Created date2023-02-11
Updated date2026-10-15
Stars in 1 day-1
Stars in 7 days-1
Rank19,031
Previous rank12,768
Rank change-6,263
7-day stars rank17,473
Previous 7-day stars rank13,656
7-day stars rank change-3,817
Total stars rank12,227
Previous total stars rank12,192
Total stars rank change-35
CountryJapan
README summary

IMPORTANT] **Notice: Outdated Implementation** This codebase was implemented prior to major updates to DreamerV3 and does not reflect those changes, which accounts for several GitHub Issues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: Run training on DMC Vision: Monitor results: 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. | | 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 ** ** 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: danijar's Dreamer-v2 tensorflow implementation: jsikyoon's Dreamer-v2 pytorch implementation: RajGhugare19's Dreamer-v2 pytorch implementation: denisyarats's DrQ-v2 original implementation:

Frequently asked questions

How many stars and forks are recorded?

NM512/dreamerv3-torch has 888 stars and 219 forks.

What is the repository rank?

NM512/dreamerv3-torch is ranked 19,031.

What language and category are recorded?

NM512/dreamerv3-torch has 888 stars, uses Python and belongs to Model Development.

Which repository is closest in rank?

NM512/dreamerv3-torch is compared with maxjcohen/transformer, ranked 19,025 with 903 stars.

README

dreamerv3-torch

[!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:

Nearby in the ranking
Similar items