Evidence item

AlphaGo Zero trained by self-play from random play with no human game data, surpassed human level, and beat the human-data-trained AlphaGo 100-0. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 7375

Source: AlphaGo Zero: Starting from scratch (Google DeepMind) · locator {} · excerpt hash sha256:febbf3155a0e8ca2c369727ddcd53deb73964ebceb908098952c0c53880e6845

Exact excerpt

Previous versions of AlphaGo initially trained on thousands of human amateur and professional games to learn how to play Go. AlphaGo Zero skips this step and learns to play simply by playing games against itself, starting from completely random play. In doing so, it quickly surpassed human level of play and defeated the previously published champion-defeating version of AlphaGo by 100 games to 0.

Linked claims

Claim	Direction	Relevance	Steps	Counted
74187da1	SUPPORT	STRONG	1	yes

Audits

None.