Limits RegistryPUBLIC RECORD
Limits RegistryDeepMind's AlphaGo Zero, described in an October 2017 Nature paper, learned Go entirely from self-play starting from random moves, using a single neural network trained via a novel reinforcement learning algorithm without any human game data. It surpassed the version of AlphaGo that had beaten Lee Sedol after about 40 days of self-play training on a single machine, and its architecture was subsequently generalized into AlphaZero for chess and shogi.
The question, scope, and sources behind this Registry record.
DeepMind's AlphaGo Zero, described in an October 2017 Nature paper, learned Go entirely from self-play starting from random moves, using a single neural network trained via a novel reinforcement learning algorithm without any human game data. It surpassed the version of AlphaGo that had beaten Lee Sedol after about 40 days of self-play training on a single machine, and its architecture was subsequently generalized into AlphaZero for chess and shogi.
AlphaGo Zero, given only the rules of Go and no human game records or handcrafted features, trained purely through self-play reinforcement learning and surpassed the strength of the AlphaGo version that defeated Lee Sedol within 40 days of training.
Change a parameter to stress-test whether a proposed result is still inside the published specification. This is an audit aid, not a proof checker.
This record has no editable parameters. Read the formal question and assumptions before challenging it.
Current frontiers derived from accepted Claims.
An observed or demonstrated result; no opposing bound is implied.
The frontier is not sacred
Most progress starts with a disagreement that survives contact with evidence. If you can push the known lower bound up or pull the upper bound down, show us the work.
≥ when you have shown that at least this value is achievable.≤ when you have shown that anything above this value is impossible.No vibes. State the value, define the scope, and link the paper, proof, code, or reproduction that lets another person check it. Editors review every challenge before the public record changes.
Challenge this recordAssertions tied to evidence, attribution, and review.
The frontier as it changed over time.
Only accepted Claims matching the current specification contribute to the displayed bounds. Strict inequalities remain open; contradictory Claims require editorial review.
1 accepted Claim, with 1 linked evidence records.
Permanent ID limitsregistry.com/limits/LR-ALPHAGO-ZERO-SELF-PLAY
No active verified bounties are linked to this Limit.
View verified bounty tracker ↗No accepted machine-checked reproductions are recorded for this Limit.
Limits Registry. LR-ALPHAGO-ZERO-SELF-PLAY. AlphaGo Zero — superhuman Go from pure self-play. 2026.