Commit Graph
1 Commits
Author SHA1 Message Date
coolguyandClaude Opus 4.7 6c9babe769 Validate strategy-memory flags under external sampling
OpenSpiel's Deep CFR records strategy samples at opponent nodes during
the traverser's tree walk; storing on traverser nodes under external
sampling drops the ρ_p reach factor and biases the average-policy
estimate. Reject that config combination at load time and add a research
note deriving why outcome sampling is unaffected while external is not.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-07 20:56:57 +09:00