LINEAiGE
AI HISTORY

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

David Silver and colleagues submitted Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm to arXiv on December 5, 2017. The paper described AlphaZero as a single algorithm that learned through self-play from random play with no domain knowledge beyond game rules and reported superhuman performance in chess, shogi, and Go.

December 5, 2017AI HISTORYVERIFIED

Historical classification

This verified record belongs to LINEAiGE's artificial-intelligence history layer beginning in 1956.

Why it matters

A documented reinforcement-learning milestone demonstrating one self-play algorithm across multiple challenging board-game domains without handcrafted domain knowledge beyond the rules.

People, organizations & technologies

PEOPLE
David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, Demis Hassabis

TECHNOLOGIES
AlphaZero, Reinforcement learning, Self-play, Monte Carlo tree search

Evidence & verification

STATE
verified

CONFIDENCE
high

LAST VERIFIED
2026-09-11T11:03:50+08:00

The original arXiv record establishes the title, authors, December 5 2017 first-submission date, and the paper's description of AlphaZero as a single algorithm learning from random play with only game rules and achieving superhuman play in chess, shogi, and Go. This record is scoped to the paper-submission milestone and does not infer a separate system-birth date, institutional geography, ancestry, influence, or causal relationships.

Sources

SOURCE 1 · PRIMARY · CLAIM-EVIDENCE

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

arXiv

PUBLISHED
2017-12-05

Trace the chronology

Record identity

LINEAiGE ID
alphazero-2017