---
title: "RSSM | Recurrent State Space Model | world-models.io"
canonical: "https://world-models.io/en/models/rssm/"
description: "The RSSM is the foundational architecture behind the Dreamer family of world models. Review RSSM: evidence, scope, limitations, and primary sources."
author: "Tyler D."
generated: "2026-10-30"
---

New: the Timeline is live. Track world model releases, papers, and benchmark updates in real time.

The Knowledge Hub for AI World Models

# RSSM

The Recurrent State Space Model (RSSM) is the foundational architecture behind the Dreamer family, combining deterministic and stochastic state components for latent dynamics modeling.

robotics

model-based-rl

simulation

embodied-ai

## What is a world model?

A world model is an AI system that learns a predictive representation of how an environment changes over time. It can use observations, actions, or language to estimate future states and possible outcomes before an agent acts. World models support planning in model-based reinforcement learning, robotics, embodied AI, autonomous driving, and interactive simulation. This site catalogs these systems with model records, research papers, benchmark context, and source links. Start with the [world models database](https://world-models.io/en/world-models-database/), compare systems on the [leaderboard](https://world-models.io/en/leaderboard/), or read the [Performance Index methodology](https://world-models.io/en/methodology/performance-index/).

## Key Attributes

Static HTML snapshot of the model record for crawlers and no-JS readers.

| Attribute | Value |
| --- | --- |
| Model | RSSM |
| Lab / Organization | DeepMind |
| Category | Latent Dynamics |
| Subtype | Latent Dynamics Architecture |
| World Model Type | Core dynamics architecture |
| Primary Domain | World model backbone |
| Architecture | Hybrid deterministic-stochastic recurrent model with encoder/decoder |
| Modality | Visual + Proprioceptive |
| Training Method | Variational inference with reconstruction and KL objectives |
| Status | active |
| Year | 2019 |
| Performance Index | 64/100 (medium confidence, v1.1) |

## About RSSM

Main editorial body preserved directly in static HTML.

The RSSM models environment dynamics in latent space using both deterministic and stochastic components. The deterministic path captures predictable transitions via a recurrent network, while the stochastic path models uncertainty through latent variables. This design forms the backbone of PlaNet, DreamerV1, V2, and V3.

RSSM is a core dynamics architecture developed by Google in 2019 for world model backbone.

## Editorial Snapshot

Short extractable facts for answer engines and no-JS readers.

| Signal | Value |
| --- | --- |
| Definition | RSSM is a core dynamics architecture developed by Google in 2019 for world model backbone. |
| Short Description | Recurrent State-Space Model: the foundational architecture behind PlaNet and the entire Dreamer family of world models. |
| Benchmark Rows | 0 |
| FAQ Entries | 1 |
| Related Models | 3 |
| Related Guides | 1 |
| Related Research Topics | 1 |
| Last Updated | 2026-02-05 |

## Notable Features

Key capabilities associated with this model.

- • Combines deterministic and stochastic state paths
- • Captures both predictable dynamics and uncertainty
- • Foundation for the entire Dreamer lineage
- • Elegantly simple yet powerful design

## Use Cases

Representative applications attached to this model record.

World model backbone

Latent dynamics modeling

Imagination-based RL

## Strengths and Limitations

Balanced assessment surfaced in static HTML.

### Strengths

- • Captures uncertainty
- • Enables long-horizon imagination
- • Proven across domains
- • Elegant design

### Limitations

- • Requires careful KL balance tuning
- • Computational overhead of stochastic components

## References and Citations

Primary references preserved in static HTML for citation extraction.

| Reference | Link |
| --- | --- |
| Hafner et al., 2019. Learning Latent Dynamics for Planning from Pixels. | [Open source](https://arxiv.org/abs/1811.04551) |

## Related Models

Nearby models linked from the current editorial record.

| Model | Category | World Model Type | Index v1.1 |
| --- | --- | --- | --- |
| [PlaNet](https://world-models.io/en/models/planet/) | Model-Based RL | Latent space planning model | 57/100 |
| [DreamerV3](https://world-models.io/en/models/dreamer-v3/) | Model-Based RL | Imagination-based dynamics model | 88/100 |
| [DreamerV2](https://world-models.io/en/models/dreamer-v2/) | Model-Based RL | Imagination-based dynamics model | 72/100 |

## Direct Comparisons

Side-by-side comparisons already connected to this model.

| Comparison | Matchup | Summary |
| --- | --- | --- |
| [DreamerV3 vs PlaNet](https://world-models.io/en/compare/dreamer-v3-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. |
| [DreamerV2 vs PlaNet](https://world-models.io/en/compare/dreamer-v2-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. |
| [DreamerV2 vs DreamerV3](https://world-models.io/en/compare/dreamer-v2-vs-dreamer-v3/) | DreamerV2 vs DreamerV3 | The Dreamer lineage's two most impactful iterations: DreamerV2 achieved human-level Atari with discrete representations, while DreamerV3 eliminated hyperparameter tuning entirely with symlog predictions. |

## Guides Referencing This Model

Crawler-readable guide links tied to this model.

| Guide | Summary |
| --- | --- |
| [RSSM Architecture Explained: Dreamer World Model](https://world-models.io/en/guides/understanding-rssm/) | A technical guide to the Recurrent State-Space Model: the foundational architecture behind PlaNet and the Dreamer family of world models. |

## Research Topics Referencing This Model

Connected research areas surfaced directly in static HTML.

| Topic | Summary |
| --- | --- |
| [Self-Supervised World Models](https://world-models.io/en/research/self-supervised-world-models/) | How self-supervised world models learn environment dynamics without rewards, from JEPA and V-JEPA to predictive latent representations. |

## Frequently Asked Questions

FAQ answers rendered directly into static HTML for extractable responses.

### Why use both deterministic and stochastic states?

The deterministic path captures predictable dynamics, while the stochastic path models uncertainty and multi-modal outcomes. Together they create a more robust world model.

## Quick Answer

Short extractable summary preserved directly in static HTML.

- RSSM is a core dynamics architecture developed by Google in 2019 for world model backbone.
- Use this page when you need a fast read on how RSSM fits into the latent dynamics landscape, then validate the details in the benchmarks, citations, and related pages.
- A key strength surfaced in the editorial record is captures uncertainty.

## Editorial Trust Signals

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: 2026-02-05.

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.](https://world-models.io/en/editorial-policy/)

Primary sources only

Last reviewed date visible

Methodology documented

Source links included

Correction channel published

Review date visible

## External Sources

Primary model and lab sources embedded in static HTML.

- [RSSM paper](https://arxiv.org/abs/1811.04551) Google primary research source
- [Google DeepMind official website](https://deepmind.google) Related lab

## References

1. [[1] Hafner et al., 2019. Learning Latent Dynamics for Planning from Pixels.](https://arxiv.org/abs/1811.04551)