---
title: "World Models (Ha & Schmidhuber) | Seminal 2018 Paper."
canonical: "https://world-models.io/en/models/ha-world-model/"
description: "The seminal 2018 'World Models' paper by Ha & Schmidhuber that popularized the concept of learned world models for RL."
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

# World Models (Ha & Schmidhuber)

The seminal 2018 paper by Ha & Schmidhuber that introduced the modern concept of world models for reinforcement learning, combining VAE, MDN-RNN, and controller components.

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 | World Models (Ha & Schmidhuber) |
| Lab / Organization | DeepMind |
| Category | Model-Based RL |
| Subtype | VAE + MDN-RNN |
| World Model Type | Generative latent dynamics model |
| Primary Domain | Game environments |
| Architecture | VAE (visual encoder) + MDN-RNN (dynamics) + linear controller |
| Modality | Visual |
| Training Method | Unsupervised VAE training + RNN dynamics learning + evolutionary policy search |
| Status | foundational |
| Year | 2018 |
| Performance Index | 48/100 (high confidence, v1.1) |

## About World Models (Ha & Schmidhuber)

Main editorial body preserved directly in static HTML.

Ha and Schmidhuber's World Models paper demonstrated that an agent can learn a compressed spatial and temporal representation of the environment, then train a policy entirely within this learned 'dream' world. The architecture uses a VAE for spatial encoding and an MDN-RNN for temporal dynamics, creating a generative model of the environment that the agent can imagine in.

World Models (Ha & Schmidhuber) is a generative latent dynamics model developed by Google Brain / IDSIA in 2018 for game environments.

## Editorial Snapshot

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

| Signal | Value |
| --- | --- |
| Definition | World Models (Ha & Schmidhuber) is a generative latent dynamics model developed by Google Brain / IDSIA in 2018 for game environments. |
| Short Description | The seminal paper that popularized the concept of world models: learning to imagine environments and training policies entirely in dreams. |
| Benchmark Rows | 1 |
| FAQ Entries | 1 |
| Related Models | 3 |
| Related Guides | 3 |
| Related Research Topics | 3 |
| Last Updated | 2026-02-10 |

## Notable Features

Key capabilities associated with this model.

- • Coined the modern usage of 'world models' in RL
- • Training policies entirely in dreams
- • VAE + RNN architecture
- • Interactive web-based demonstrations

## Use Cases

Representative applications attached to this model record.

Game playing (VizDoom, CarRacing)

Imagination-based policy learning

Conceptual demonstration of world models

## Strengths and Limitations

Balanced assessment surfaced in static HTML.

### Strengths

- • Conceptually foundational
- • Elegant and interpretable
- • Demonstrated dream-based training
- • Highly influential

### Limitations

- • Simple environments only
- • VAE reconstruction loss limitations
- • Limited scalability

## Benchmarks

Published benchmark evidence attached to this model record.

| Benchmark | Metric | Result | Source |
| --- | --- | --- | --- |
| CarRacing-v0 | Avg Score 906 / 1000 | Competitive (dream-trained) | [Source](https://arxiv.org/abs/1803.10122) |

## References and Citations

Primary references preserved in static HTML for citation extraction.

| Reference | Link |
| --- | --- |
| Ha, D. & Schmidhuber, J., 2018. World Models. NeurIPS 2018. | [Open source](https://arxiv.org/abs/1803.10122) |

## 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 |
| [DreamerV2](https://world-models.io/en/models/dreamer-v2/) | Model-Based RL | Imagination-based dynamics model | 72/100 |
| [RSSM](https://world-models.io/en/models/rssm/) | Latent Dynamics | Core dynamics architecture | 64/100 |

## Direct Comparisons

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

| Comparison | Matchup | Summary |
| --- | --- | --- |
| [Ha & Schmidhuber World Model vs DreamerV3](https://world-models.io/en/compare/ha-world-model-vs-dreamer-v3/) | Ha & Schmidhuber World Model vs DreamerV3 | The original 2018 'World Models' paper vs. the current state-of-the-art: how five years of research transformed a foundational concept into a domain-general world model agent. |
| [AMI vs Ha World Model](https://world-models.io/en/compare/ami-vs-ha-world-model/) | AMI vs Ha World Model | Two pioneering cognitive-inspired world models: Ha's 2018 World Model introduced the VAE+RNN+Controller architecture, while AMI proposes an autonomous machine intelligence framework inspired by biological cognition. |

## Guides Referencing This Model

Crawler-readable guide links tied to this model.

| Guide | Summary |
| --- | --- |
| [What Is a World Model? A Beginner's Guide](https://world-models.io/en/guides/world-models-for-beginners/) | A clear introduction to AI world models: learned internal models that predict how an environment changes, how actions affect the future, and why this matters for robotics, reinforcement learning, and embodied AI. |
| [Building World Models: A Practical Guide](https://world-models.io/en/guides/building-world-models/) | A practical guide to implementing world models: from choosing architectures and training setups to debugging dynamics learning and policy optimization. |
| [World Model Papers: Ha & Schmidhuber, DreamerV3, and More](https://world-models.io/en/guides/world-models-research-papers/) | A practical, source-led reading path through world model papers, from Ha & Schmidhuber's 2018 foundational paper to the DreamerV3 world model paper (2023), latent dynamics, planning, simulators, and self-supervised approaches. |

## Research Topics Referencing This Model

Connected research areas surfaced directly in static HTML.

| Topic | Summary |
| --- | --- |
| [Model-Based Reinforcement Learning](https://world-models.io/en/research/model-based-rl/) | 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](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. |
| [World Models: A Comprehensive Survey](https://world-models.io/en/research/world-models-survey/) | A survey of AI world models covering taxonomy, leading architectures, landmark systems, open challenges, and future research directions. |

## Frequently Asked Questions

FAQ answers rendered directly into static HTML for extractable responses.

### Is this where the term 'world model' comes from?

The concept existed earlier (e.g., Schmidhuber 1990), but Ha & Schmidhuber's 2018 paper popularized the term in the modern deep RL context and inspired the current wave of world model research.

## Quick Answer

Short extractable summary preserved directly in static HTML.

- World Models (Ha & Schmidhuber) is a generative latent dynamics model developed by Google Brain / IDSIA in 2018 for game environments.
- Use this page when you need a fast read on how World Models (Ha & Schmidhuber) fits into the model-based rl landscape, then validate the details in the benchmarks, citations, and related pages.
- A key strength surfaced in the editorial record is conceptually foundational.

## 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: 2026-02-10.

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.

- [World Models (Ha & Schmidhuber) paper](https://arxiv.org/abs/1803.10122) Google Brain / IDSIA primary research source
- [World Models (Ha & Schmidhuber) official page](https://worldmodels.github.io) Google Brain / IDSIA official page
- [Google DeepMind official website](https://deepmind.google) Related lab

## References

1. [[1] Ha, D. & Schmidhuber, J., 2018. World Models. NeurIPS 2018.](https://arxiv.org/abs/1803.10122)