# danijar/dreamerv3

Mastering Diverse Domains through World Models

Repository: https://github.com/danijar/dreamerv3
Canonical: https://ross.abutalabs.com/products/dreamerv3
Homepage: https://danijar.com/dreamerv3
Language: Python
License: MIT
License Family: permissive
Topics: artificial-intelligence, general, minecraft, reinforcement-learning, world-models, jax
Last push: 2026-05-25T06:40:27+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 84, release rhythm 35, longevity 94
- inputs: {"age_days": 1327, "days_push": 100, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3704, forks 598 (observed 2026-08-28T04:08:15.062108+00:00)

## What it is
A Python/JAX reimplementation of DreamerV3, a model-based reinforcement learning algorithm that learns a world model and trains an actor-critic policy from imagined trajectories. It masters diverse control tasks (Atari, Minecraft, Crafter, robotics) with fixed hyperparameters and favorable scaling properties.

## Use cases
- train a reinforcement learning agent that works across many tasks without hyperparameter tuning
- reproduce DreamerV3 benchmark results on Atari or Crafter
- learn a world model from sensory inputs and train policies from imagined trajectories
- apply model-based RL to Minecraft or other diverse control domains
- experiment with scalable RL algorithms in JAX
- study data-efficient reinforcement learning with larger world models

## When to choose
- you need a general RL algorithm with fixed hyperparameters across domains
- you want a well-cited, actively maintained reference implementation of DreamerV3
- you prefer JAX for GPU-accelerated RL research

## When to avoid
- you need a simple tuned RL baseline for a single specific environment
- you lack GPU resources, since world model training is compute-intensive
- you need a production RL service rather than research code

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, reinforcement-learning, simulation
- domain: artificial-intelligence, reinforcement-learning, machine-learning, gaming-tools
- platform: python
- tags: world-models, jax, model-based-rl, actor-critic, research-code, linux, macos, gpu

## Member repositories
- danijar/dreamerv3 (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:15.062108+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:30:59.956094+00:00, confidence not recorded.
  - readme: https://github.com/danijar/dreamerv3 (fetched 2026-08-28T04:08:15.062108+00:00, sha 96f03681b484)
  - homepage: https://danijar.com/dreamerv3 (fetched 2026-08-29T09:24:36.775649+00:00, sha 07d45e5779ee)
  - registry_pypi: https://pypi.org/pypi/dreamerv3/json (fetched 2026-08-29T09:24:36.784569+00:00, sha 7eeea8f757ce)
- Data as of 2026-08-30T08:39:29.467469+00:00.