coolguyandClaude Haiku 4.5 6b8c36ebb2 docs: opponent_policy 비교에 동일 조건 self_play_league run 추가 ...

같은 hyperparameter (512x3, 2x updates, argmax_tiebreak)에 opponent_policy
만 self_play_league로 다른 run과의 iteration별 비교 표 추가. iter 350
시점에서 Random WR 38%p 격차 (network 34% vs league 72%) 확인 — 발산
가설을 실증.

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>

2026-05-07 13:56:43 +09:00

..

classic-port-notes.md

정책 인터페이스로 네이밍 정리

2026-05-06 22:52:04 +09:00

deep-cfr-batched-evaluation-2026-05-07.md

Deep CFR evaluation 배칭 및 병렬화 추가

2026-05-07 03:42:00 +09:00

deep-cfr-evaluation-profile-2026-05-07.md

Deep CFR evaluation 배칭 및 병렬화 추가

2026-05-07 03:42:00 +09:00

deep-cfr-evaluation-profile-plan.md

Deep CFR evaluation 프로파일링 메트릭 추가

2026-05-07 03:10:19 +09:00

deep-cfr-legacy-experiment-reproduction.md

Deep CFR 재현 config 이름 정리

2026-05-07 01:15:34 +09:00

deep-cfr-legacy-runtime-comparison-2026-05-07.md

Deep CFR evaluation 배칭 및 병렬화 추가

2026-05-07 03:42:00 +09:00

deep-cfr-opponent-policy-network-divergence-2026-05-07.md

docs: opponent_policy 비교에 동일 조건 self_play_league run 추가

2026-05-07 13:56:43 +09:00

deep-cfr-profile-2026-05-07.md

Deep CFR 프로파일링 메트릭 추가

2026-05-07 02:50:35 +09:00

deep-cfr-profile-advantage-memory-split-2026-05-07.md

Deep CFR advantage memory를 player별로 분리

2026-05-07 02:59:03 +09:00

deep-cfr-regret-fallback-audit-2026-05-07.md

Deep CFR regret fallback audit metrics 추가

2026-05-07 05:23:23 +09:00

deep-cfr-v0-gap-vs-coolrl.md

Deep CFR traversal을 Cython 엔진으로 교체

2026-05-07 02:25:33 +09:00

deep-cfr-v0-plan.md

Deep CFR v0 계획 문서 추가

2026-05-06 23:10:46 +09:00

fast-engine-next-optimizations.md

고속 엔진 undo stack 추가

2026-05-06 22:02:04 +09:00

test-coverage-notes.md

Add test coverage notes

2026-05-07 02:11:16 +09:00