fix(matrix): a practice board that cannot exist must degrade, not block - #46
Merged
Conversation
Practice runs at a different board so that building a player is not memorising the graded one. Some games cannot offer a different board: a packaged reference derives its contract at one seed and nowhere else. Verified on CartPole, whose contract builds at seed 7 and refuses at seed 1000010 with "mark survived-50-steps never fires on the reference playthrough". Measured cost of blocking instead: all four CartPole cells of a twenty-cell arena blocked, and the transfer statistic covered four games rather than five. An entire game left the study because of a seed offset it never asked for. The offset board is still tried first. When a game refuses it, practice happens on the cell's own seed and the row says so, because an author who practised on the board it was graded on is a weaker measurement and a reader has to be able to tell those cells apart. A game that builds at neither is still blocked, with the reason.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Practice runs at a different board so building a player is not memorising the graded one. Some games cannot offer a different board: a packaged reference derives its contract at one seed and nowhere else.
Verified directly: CartPole builds at seed 7 and refuses at seed 1000010 with
mark survived-50-steps never fires on the reference playthrough.Measured cost of blocking instead: all four CartPole cells of a twenty-cell arena blocked, and the transfer statistic covered four games rather than five. An entire game left the study because of a seed offset it never asked for.
The offset board is still tried first. When a game refuses it, practice happens on the cell's own seed and the row says so — an author that practised on the board it was graded on is a weaker measurement, and a reader has to be able to tell those cells apart. A game that builds at neither is still blocked, with the reason.
Local: 20 of 20 test files, boundary check, 0 typecheck errors.