The comparison & result
The experiment made one policy abandon its hand whenever an opponent exposed two melds. The comparison policy continued to assess its own hand rather than folding at that fixed trigger.
The report described roughly two wins for the automatic folder for every three wins by the comparison policy, without a lower deal-in rate. That suggests a limitation of the tested trigger. Exposed melds still matter, alongside your hand’s value, progress and available discards.
At your table
- Three-plus tiles from ready against a threatening table — reassess the risk of discarding; past discards do not establish safety under every ruleset
- NOT a blanket rule: a ready hand with a live wait keeps playing
Check your table’s scoring rules before applying the finding. Read the Hong Kong reference.
How it was tested
Tested in the Hé Fēn Lab: 100,000 hands — mechanical fold-at-two-melds against normal judgment, seats swapped so the deal is fair.
The players were software policies, not human participants. This report describes the published experiment; it does not establish the best move for every possible hand or opponent.
Results without a published uncertainty interval should be read as point estimates. Similar results do not prove two choices are equivalent.
Read the Lab’s method and limitationsPublished by Hé Fēn Mahjong. Ask about this finding or suggest a correction.