Static HTML snapshot of the model record for crawlers and no-JS readers.
| Attribute | Value |
|---|---|
| Model | DreamerV3 |
| Lab / Organization | DeepMind |
| Category | Model-Based RL |
| Subtype | Latent Dynamics Model |
| World Model Type | Imagination-based dynamics model |
| Primary Domain | General reinforcement learning |
| Architecture | RSSM with discrete representations, symlog predictions, KL-balanced objective |
| Modality | Visual + Proprioceptive |
| Training Method | Self-supervised world model learning + imagination-based policy optimization |
| Status | active |
| Year | 2023 |
| Performance Index | 88/100 (high confidence, v1.1) |
Main editorial body preserved directly in static HTML.
DreamerV3 learns a world model from experience and uses it to train an actor-critic policy entirely within imagination. It achieves superhuman performance across a wide range of domains (Atari, DMControl, Minecraft, and more), all with a single set of hyperparameters. The model uses discrete representations with symlog predictions and KL-balanced objectives to learn robust latent dynamics across vastly different environments.
DreamerV3 is an imagination-based dynamics model developed by Google DeepMind in 2023 for general reinforcement learning.
Short extractable facts for answer engines and no-JS readers.
| Signal | Value |
|---|---|
| Definition | DreamerV3 is an imagination-based dynamics model developed by Google DeepMind in 2023 for general reinforcement learning. |
| Short Description | A general algorithm for mastering diverse domains with fixed hyperparameters through world model learning. |
| Benchmark Rows | 3 |
| FAQ Entries | 2 |
| Related Models | 4 |
| Related Guides | 6 |
| Related Research Topics | 6 |
| Last Updated | 2026-07-24 |
Key capabilities associated with this model.
Representative applications attached to this model record.
Balanced assessment surfaced in static HTML.
Primary references preserved in static HTML for citation extraction.
| Reference | Link |
|---|---|
| Hafner et al., 2023. Mastering Diverse Domains through World Models. arXiv:2301.04104 | Open source |
Nearby models linked from the current editorial record.
Side-by-side comparisons already connected to this model.
| Comparison | Matchup | Summary |
|---|---|---|
| DreamerV3 vs PlaNet | DreamerV3 vs PlaNet | DreamerV3 represents the evolution of PlaNet's core ideas. Both use the RSSM architecture, but DreamerV3 adds discrete representations, symlog predictions, and fixed hyperparameters to achieve state-of-the-art performance across diverse domains. |
| World Models vs LLMs | World Models vs Large Language Models | World models and LLMs represent fundamentally different approaches to AI. World models learn causal dynamics of physical environments; LLMs learn statistical patterns over text. Both are essential for the future of AI. |
| DreamerV3 vs MuZero | DreamerV3 vs MuZero | Both are landmark world model systems, but with fundamentally different architectures. DreamerV3 uses latent imagination with actor-critic learning, while MuZero uses abstract learned dynamics with Monte Carlo tree search. |
| Model-Based RL vs Model-Free RL | Model-Based RL vs Model-Free RL | Model-based RL learns a world model for imagination-based planning. Model-free RL learns directly from interaction without an internal model. Each approach has distinct strengths depending on the application domain. |
| NVIDIA Cosmos vs DreamerV3 | NVIDIA Cosmos vs DreamerV3 | Cosmos and DreamerV3 represent two different scales and approaches to world modeling: Cosmos is a foundation-scale video world model platform for physical AI, while DreamerV3 is a sample-efficient RL agent with learned dynamics. |
| DreamerV3 vs DIAMOND | DreamerV3 vs DIAMOND | DreamerV3 and DIAMOND are both model-based RL agents that train policies via imagination, but they use fundamentally different dynamics models: RSSM latent dynamics vs. pixel-space diffusion models. |
| IRIS vs DreamerV3 | IRIS vs DreamerV3 | IRIS and DreamerV3 are both leading model-based RL agents but use fundamentally different world model architectures: autoregressive token prediction vs. RSSM latent dynamics. |
| DreamerV2 vs PlaNet | DreamerV2 vs PlaNet | Both use the RSSM architecture for latent dynamics, but DreamerV2 introduced discrete representations that dramatically improved performance. PlaNet pioneered the approach; DreamerV2 perfected it for Atari-scale environments. |
Crawler-readable guide links tied to this model.
| Guide | Summary |
|---|---|
| World Models for Beginners | A comprehensive introduction to AI world models: what they are, how they work, and why they matter for the future of robotics, reinforcement learning, and embodied AI. |
| Understanding the RSSM Architecture | A technical guide to the Recurrent State-Space Model: the foundational architecture behind PlaNet and the Dreamer family of world models. |
| Building World Models: A Practical Guide | A practical guide to implementing world models: from choosing architectures and training setups to debugging dynamics learning and policy optimization. |
| World Models for Robotics | How to use world models for robot learning: from simulation-based training to real-world deployment and sim-to-real transfer. |
| How to Read World Models Papers | A practical reading path through world-model research, from foundational concepts to latent dynamics, planning, simulators, and self-supervised approaches. |
| World Models vs Large Language Models: A Practitioner's Guide | How world models differ from LLMs in objective, architecture and capability, and why both paradigms are likely to converge on the path to general-purpose AI. |
Connected research areas surfaced directly in static HTML.
| Topic | Summary |
|---|---|
| Model-Based Reinforcement Learning | What model-based reinforcement learning is, how world models enable imagination-based planning, and why Dreamer, MuZero, PlaNet, and TD-MPC2 matter. |
| Self-Supervised World Models | How self-supervised world models learn environment dynamics without rewards, from JEPA and V-JEPA to predictive latent representations. |
| World Models for Robotics | How world models improve robot learning, learned simulation, safe exploration, and sim-to-real transfer across manipulation, navigation, and control. |
| World Models vs LLMs | The key differences between world models and LLMs across objective, architecture, planning, physical reasoning, and embodied AI use cases. |
| World Models: A Comprehensive Survey | A survey of AI world models covering taxonomy, leading architectures, landmark systems, open challenges, and future research directions. |
| World Model Evaluation | How to evaluate world models across rollout quality, benchmark performance, planning utility, and downstream transfer instead of relying on visual plausibility alone. |
Recent timeline events connected to this model.
| Event | Published | Source | Summary |
|---|---|---|---|
| New benchmark results: DreamerV3 surpasses human performance on 7 additional Atari games | 2026-03-11 | Papers With Code | Updated benchmark evaluations confirm DreamerV3 now achieves superhuman performance on 57 out of 57 Atari 100K games... |
| Leaderboard update: Performance Index recalculated with March 2026 benchmark data | 2026-03-02 | world-models.io Editorial | The world-models. io Performance Index has been recalculated using the latest benchmark data. |
FAQ answers rendered directly into static HTML for extractable responses.
DreamerV3 introduces symlog predictions, fixed hyperparameters across domains, and discrete latent representations that enable robust performance without per-domain tuning.
Yes. DreamerV3's world model approach is applicable to robotics, especially in simulation-to-real transfer scenarios where sample efficiency matters.
Short extractable summary preserved directly in static HTML.
Editorial provenance and refresh policy preserved directly in static HTML.
Published by world-models.io editorial board.
Lead editor Tyler D. - Technical editor, methodology and benchmark analysis.
This model page synthesizes primary papers, official model pages, benchmark evidence, and related world-models.io context into a reference resource.
Each editorial page is assembled from primary sources, normalized into extractable summaries, checked for factual drift, and reviewed before publication or major refreshes. Last reviewed: 2026-07-24.
Pages are refreshed when a new paper, benchmark, release, architecture update, or stronger primary source materially changes the answer a reader or AI system should retrieve.
Each page links back to relevant primary sources and keeps a stable canonical URL so readers can verify claims, trace context, and reference the most up-to-date version. See the editorial policy.
Primary model and lab sources embedded in static HTML.