---
id: "2017-12-05-alphazero"
url: "https://postcutoff.com/e/2017-12-05-alphazero/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2017-12-05"
date_precision: day
category: research
importance: 5
confidence: high
status: [Confirmed]
sources: 3
editor: human editor
human_review: null
version: "2026-10-04"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2017-12-05-alphazero/

# AlphaGo Zero and AlphaZero master games through pure self-play

AlphaGo Zero (Nature, October 2017) learned Go from scratch with no human games and beat the version that defeated Lee Sedol 100–0; AlphaZero (December 2017) generalized the method to chess and shogi.

## Key facts
- AlphaGo Zero Nature paper published 18 October 2017
- AlphaGo Zero beat AlphaGo Lee 100–0
- AlphaZero preprint arXiv 1712.01815 (5 December 2017); Science paper December 2018
- AlphaZero defeated Stockfish (chess) and Elmo (shogi) after hours of self-play training

## What happened

DeepMind showed that a single algorithm combining a neural network with tree search, trained only by playing against itself, reached superhuman strength in three classic board games.

## Why it matters

Proved that learning from self-generated experience can exceed human knowledge — an idea that resurfaced in RL-trained reasoning models (o1, R1) in 2024–2025.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): in its training data
- Claude Opus 5.5 (training cutoff June 2026): in its training data
- Gemini 4 Hydrogen (training cutoff March 2026): in its training data
- Grok 4.7 (training cutoff May 2026): in its training data

## Sources

1. [Mastering Chess and Shogi by Self-Play with a General RL Algorithm (arXiv)](https://arxiv.org/abs/1712.01815) (arxiv.org, paper)
2. [Mastering the game of Go without human knowledge (Nature, DOI)](https://doi.org/10.1038/nature24270) (doi.org, paper)
3. [A general reinforcement learning algorithm that masters chess, shogi, and Go (Science, DOI)](https://doi.org/10.1126/science.aar6404) (doi.org, paper)

## Changes

- 2026-09-29 (filed): Created

## Related

- 2024-09-12: [OpenAI o1: reasoning models trained with reinforcement learning](https://postcutoff.com/e/2024-09-12-openai-o1/index.md)
- 2016-03-15: [AlphaGo defeats Lee Sedol 4–1 at Go](https://postcutoff.com/e/2016-03-15-alphago-lee-sedol/index.md)