---
title: "Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model"
description: "MuZero replaces the perfect simulator inside AlphaZero-style search with a learned latent model that predicts only reward, policy, and value. Follow the three learned functions, the search-to-training loop, the Atari evidence, and the precise boundary behind the phrase without rules."
canonical_url: "https://fanout.sh/daily/2026-11-04-muzero-learned-model-planning"
md_url: "https://fanout.sh/daily/2026-11-04-muzero-learned-model-planning.md"
last_updated: "2026-11-04"
access: "public"
---

# Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model

MuZero replaces the perfect simulator inside AlphaZero-style search with a learned latent model that predicts only reward, policy, and value. Follow the three learned functions, the search-to-training loop, the Atari evidence, and the precise boundary behind the phrase without rules.

## Paper details

- Authors: Julian Schrittwieser et al.

- Venue: Nature 2020

- Track: AI Research

- Difficulty: Hard

- Reading time: 13 min

- Original paper: https://arxiv.org/abs/1911.08265v2

## What you will learn

- Why a planning model can ignore future pixels and preserve only the quantities tree search consumes.

- How representation, dynamics, and prediction functions let Monte Carlo tree search expand an imagined latent tree.

- What the board-game and Atari results establish, and why deterministic dynamics, compute, and model error still bound the result.

## Continue exploring

[Start with AlphaGo's search loop](https://fanout.sh/daily/2026-08-15-alphago-neural-tree-search): Compare a planner that receives game rules with MuZero's replacement: a learned hidden-state transition, reward, policy, and value model.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md