Editorial definition preserved directly in static HTML.
Latent dynamics models learn compressed representations of environment dynamics in a latent (hidden) space, enabling efficient prediction and planning without operating in pixel space.
Architectures that learn compressed representations of world dynamics in latent space.
Static category overview generated from local editorial data.
| Attribute | Value |
|---|---|
| Category | Latent Dynamics |
| Description | Architectures that learn compressed representations of world dynamics in latent space. |
| Definition | Latent dynamics models learn compressed representations of environment dynamics in a latent (hidden) space, enabling efficient prediction and planning without operating in pixel space. |
| Related Models | 5 |
| Related Research | 1 |
| Related Guides | 1 |
Additional editorial context preserved directly in static HTML.
Latent-space prediction made modern world modeling far more efficient by preserving decision-relevant structure without paying the cost of direct pixel-space rollouts.
This category links the architectural ideas behind latent representations to the systems and research pages where those ideas became influential in practice.
| Model | Lab | Category | Year |
|---|---|---|---|
| RSSM | Latent Dynamics | 2019 | |
| PlaNet | Model-Based RL | 2019 | |
| DreamerV3 | Google DeepMind | Model-Based RL | 2023 |
| DreamerV2 | Model-Based RL | 2021 | |
| World Models (Ha & Schmidhuber) | Google Brain / IDSIA | Model-Based RL | 2018 |
| 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. |
| Guide | Summary |
|---|---|
| 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. |
FAQ answers rendered directly into static HTML for extractable responses.
Latent dynamics models predict state transitions in a compressed hidden space rather than directly in pixels, making planning more efficient.
Latent space captures the relevant structure of an environment while reducing computation and noise from raw observations.
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 Bernard Grenat.
This category page maintains a stable editorial definition and connects it to related models, research topics, guides, and source-backed context.
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: 2026-06-21.
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.
Representative external references connected to this category through related models and research topics.