---
title: "Mastering the game of Go with deep neural networks and tree search"
description: "This paper asks how a computer can choose a strong Go move when the game tree is far too large to enumerate. Read it to see how a learned policy concentrates search on promising moves, how a value network estimates who is ahead before a game ends, and how Monte Carlo tree search turns those estimates into professional-level play under a large compute budget."
canonical_url: "https://fanout.sh/daily/2026-08-15-alphago-neural-tree-search"
md_url: "https://fanout.sh/daily/2026-08-15-alphago-neural-tree-search.md"
last_updated: "2026-08-15"
access: "public"
---

# Mastering the game of Go with deep neural networks and tree search

This paper asks how a computer can choose a strong Go move when the game tree is far too large to enumerate. Read it to see how a learned policy concentrates search on promising moves, how a value network estimates who is ahead before a game ends, and how Monte Carlo tree search turns those estimates into professional-level play under a large compute budget.

## Paper details

- Authors: Silver et al.

- Venue: Nature 2016

- Track: AI Research

- Difficulty: Easy

- Reading time: 35 min

- Original paper: https://deepmind-media.storage.googleapis.com/alphago/AlphaGoNaturePaper.pdf

## What you will learn

- How a policy network reduces the effective breadth of search while a value network reduces the effective depth.

- Why expert imitation, self-play reinforcement learning, and independent value-training positions solve different parts of the problem.

- How policy priors, visit counts, value estimates, and rollouts combine inside Monte Carlo tree search, and which compute and evaluation limits qualify the result.

## Continue exploring

[Explore reinforcement learning](https://fanout.sh/knowledge-graph?node=ai-research%3Amodule%3Areinforcement-learning): Connect AlphaGo's self-play, policy, and value functions to Fanout's reinforcement-learning path, then continue into agents, environments, rewards, policy gradients, and modern reasoning systems.

---
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