---
title: "MuZero | Learned Planning Without Rules | world-models.io"
canonical: "https://world-models.io/en/models/muzero/"
description: "MuZero masters Go, chess, shogi, and Atari by learning a world model and planning with MCTS - without knowing game rules."
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

# MuZero

MuZero learns a world model that predicts reward, value, and policy without knowledge of game rules, achieving superhuman performance through Monte Carlo tree search planning.

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 | MuZero |
| Lab / Organization | DeepMind |
| Category | Model-Based RL |
| Subtype | Learned Model + Search |
| World Model Type | Abstract learned dynamics + MCTS |
| Primary Domain | Games / Planning |
| Architecture | Representation + Dynamics + Prediction networks with MCTS planning |
| Modality | Board states / Visual (Atari) |
| Training Method | Self-play with learned dynamics model and MCTS |
| Status | foundational |
| Year | 2020 |
| Performance Index | 78/100 (high confidence, v1.1) |

## About MuZero

Main editorial body preserved directly in static HTML.

MuZero learns a world model that predicts reward, value, and policy without requiring knowledge of environment rules. It combines this learned model with Monte Carlo tree search (MCTS) to achieve superhuman performance in Go, chess, shogi, and Atari. Unlike AlphaZero, MuZero does not need a perfect simulator.

MuZero is an abstract learned dynamics + mcts developed by Google DeepMind in 2020 for games / planning.

## Editorial Snapshot

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

| Signal | Value |
| --- | --- |
| Definition | MuZero is an abstract learned dynamics + mcts developed by Google DeepMind in 2020 for games / planning. |
| Short Description | Masters games without knowing the rules by learning a world model for planning via Monte Carlo tree search. |
| Benchmark Rows | 3 |
| FAQ Entries | 1 |
| Related Models | 2 |
| Related Guides | 2 |
| Related Research Topics | 2 |
| Last Updated | 2026-02-20 |

## Notable Features

Key capabilities associated with this model.

- • No game rules required
- • Learned dynamics model for MCTS
- • Superhuman across board games and Atari
- • Elegant three-network architecture

## Use Cases

Representative applications attached to this model record.

Board games

Atari games

Planning under uncertainty

Decision-making

## Strengths and Limitations

Balanced assessment surfaced in static HTML.

### Strengths

- • No rules needed
- • Superhuman game play
- • Elegant architecture
- • Proven at scale

### Limitations

- • Computationally expensive MCTS
- • Limited to discrete action spaces initially
- • Requires large-scale compute

## Benchmarks

Published benchmark evidence attached to this model record.

| Benchmark | Metric | Result | Source |
| --- | --- | --- | --- |
| Go | Elo 5000 Elo+ | Superhuman | [Source](https://arxiv.org/abs/1911.08265) |
| Chess | Elo 3600 Elo+ | Superhuman | [Source](https://arxiv.org/abs/1911.08265) |
| Atari | Mean HNS 7.31 x human | State-of-the-art | [Source](https://arxiv.org/abs/1911.08265) |

## References and Citations

Primary references preserved in static HTML for citation extraction.

| Reference | Link |
| --- | --- |
| Schrittwieser et al., 2020. Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model. Nature. | [Open source](https://arxiv.org/abs/1911.08265) |

## Related Models

Nearby models linked from the current editorial record.

| Model | Category | World Model Type | Index v1.1 |
| --- | --- | --- | --- |
| [Predictron](https://world-models.io/en/models/predictron/) | Model-Based RL | Abstract internal dynamics model | 43/100 |
| [DreamerV3](https://world-models.io/en/models/dreamer-v3/) | Model-Based RL | Imagination-based dynamics model | 88/100 |

## Direct Comparisons

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

| Comparison | Matchup | Summary |
| --- | --- | --- |
| [DreamerV3 vs MuZero](https://world-models.io/en/compare/dreamer-v3-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](https://world-models.io/en/compare/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. |
| [DreamerV3 vs TD-MPC2](https://world-models.io/en/compare/dreamer-v3-vs-td-mpc2/) | DreamerV3 vs TD-MPC2 | Two leading model-based RL agents with different philosophies: DreamerV3 uses imagination-based actor-critic learning, while TD-MPC2 combines temporal-difference learning with model-predictive control for multi-task mastery. |
| [MuZero vs TD-MPC2](https://world-models.io/en/compare/muzero-vs-td-mpc2/) | MuZero vs TD-MPC2 | Both use learned dynamics models for planning, but MuZero uses Monte Carlo tree search for deep discrete planning while TD-MPC2 uses model-predictive control for continuous multi-task settings. |
| [MuZero vs DreamerV3](https://world-models.io/en/compare/muzero-vs-dreamer-v3/) | MuZero vs DreamerV3 | Two titans of model-based RL with fundamentally different approaches: MuZero learns a value-equivalent model for search-based planning, while DreamerV3 learns a generative world model for imagination-based policy optimization. |
| [Predictron vs MuZero](https://world-models.io/en/compare/predictron-vs-muzero/) | Predictron vs MuZero | Both learn abstract dynamics models for planning without requiring environment reconstruction, but Predictron was an early prototype while MuZero became the definitive realization of value-equivalent model learning. |
| [Predictron vs MuZero](https://world-models.io/en/compare/predictron-vs-muzero/) | Predictron vs MuZero | Two DeepMind models that learn abstract value-equivalent dynamics. The Predictron (2017) introduced the concept of learned transition models in abstract space; MuZero (2020) scaled this to superhuman game play without knowing the rules. |

## 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. |
| [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. |
| [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.

### How does MuZero differ from AlphaZero?

AlphaZero requires a perfect simulator of game rules, while MuZero learns its own dynamics model from experience, making it applicable to environments without known rules.

## Quick Answer

Short extractable summary preserved directly in static HTML.

- MuZero is an abstract learned dynamics + mcts developed by Google DeepMind in 2020 for games / planning.
- Use this page when you need a fast read on how MuZero 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 no rules needed.

## 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: 2026-02-20.

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.

- [MuZero paper](https://arxiv.org/abs/1911.08265) Google DeepMind primary research source
- [Google DeepMind official website](https://deepmind.google) Related lab

## References

1. [[1] Schrittwieser et al., 2020. Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model. Nature.](https://arxiv.org/abs/1911.08265)