---
title: 'Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model'
license: CC-BY-4.0
license_url: https://creativecommons.org/licenses/by/4.0/
license_note: 'paper is arXiv non-exclusive distribution license (verified on arXiv abs page 2026-11-12); this pointer note is our own words and is CC BY 4.0; we link to the paper rather than reproduce it'
source: https://iinventedlight.com/library/notes/1911-08265-muzero.md
source_license: 'arXiv non-exclusive distribution license'
attribution: 'Pointer by iinventedlight (AI-assisted). Source: Julian Schrittwieser, Ioannis Antonoglou, Thomas Hubert, and 9 coauthors (listed on the arXiv abs page), Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model (arXiv non-exclusive distribution license). This note links to the paper rather than reproducing it.'
author: 'iinventedlight (AI-assisted)'
date: 2026-11-12
status: published
approved_by: "Cole Withington, 2026-11-12 14:44 PT, Librarian chat widget t51s316: \"Yes, publish all 100 second-list arXiv notes\""
checked_on: 2026-11-12
as_of: 2026-11-12
confidence: medium
untested: 'Pointer note only. Paper not reproduced. Abs page and license checked 2026-11-12.'
category: arxiv
topic_area: 'ai-research: AI-for-science'
tags: arxiv, AI-for-science, reinforcement-learning, planning
arxiv_id: 1911.08265
alias: 1911.08265-muzero
type: pointer
format: pointer
sources:
  - id: S1
    title: 'Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model'
    publisher: arXiv
    authors: 'Julian Schrittwieser, Ioannis Antonoglou, Thomas Hubert, and 9 coauthors (listed on the arXiv abs page)'
    url: https://arxiv.org/abs/1911.08265
    version_read: 'v2 (21 Feb 2020)'
    accessed: 2026-11-12
    license: 'arXiv non-exclusive distribution license'
---
# Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model

## Summary
[Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://arxiv.org/abs/1911.08265) (2019) introduced MuZero, which learns a model of the environment and then plans in that model, without being given the official rules or a perfect simulator. The authors show strong results on Atari, Go, chess, and shogi, extending the AlphaZero line to settings where the dynamics are not known in advance.

What it introduced: a model-based planning agent that trains a dynamics model, a value head, and a policy head together, then uses tree search in the learned model rather than in a hand-specified simulator.

What it led to: later model-based reinforcement learning and planning work that treats a learned world model as the place where search happens. Live note: [1712-01815-alphazero](https://iinventedlight.com/library/notes/1712-01815-alphazero/).

Use it when you want planning without an official game engine, after reading AlphaZero. Where to read it: https://arxiv.org/abs/1911.08265 (v2 (21 Feb 2020)).

The paper is posted on arXiv under the arXiv non-exclusive distribution license. This note links to it rather than reproducing it. The note itself is CC BY 4.0.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Pointer by iinventedlight (AI-assisted). Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it.

---

Agents: [/agents.md](/agents.md) | [/.well-known/agent-library.json](/.well-known/agent-library.json).
