coolguy/coorl-lost-cities
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
180 Commits 3 Branches 0 Tags
1ee329250e49c4dbdb1f111b3d0a159dbe8ae0c4
Commit Graph
180 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
coolguyandClaude Haiku 4.5 cf67bc2198 Add color_shared + attention 1000-iteration experimental config 
- hidden_size: 256 (smaller for faster iteration)
- num_layers: 2
- color_attention_layers: 2, color_attention_heads: 8
- max_iterations: 1000
- advantage/strategy_updates: 256 (reduced from 512)
- Ready for experimental training run

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
 2026-05-07 09:21:50 +09:00
coolguyandClaude Haiku 4.5 b7fce79f5b Add example configs for color_shared network architectures 
- Add deep_cfr_color_shared_512x3.yaml: color_shared without attention
- Add deep_cfr_color_shared_attention_512x3.yaml: color_shared with 2-layer attention
- Both use 512 hidden size and 3 MLP layers
- Configs are ready for experimental training runs

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
 2026-05-07 09:19:02 +09:00
coolguyandClaude Haiku 4.5 cee8849e04 Add backward-compatible color_shared network architecture 
- Add network.kind field to config (mlp/color_shared)
- Implement ColorSharedNetwork that:
  - Splits input into 5 equal color blocks
  - Encodes each block with shared weights
  - Pools with mean/max aggregation
  - Concatenates pooled embeddings with remainder
  - Outputs same action logits as MLP
- Add ColorAttention for optional self-attention over color embeddings
- Add network.color_attention_layers and color_attention_heads config
- Maintain full backward compatibility (default kind=mlp)
- Add 28 comprehensive tests covering all architectures

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
 2026-05-07 09:18:13 +09:00
coolguyandClaude Haiku 4.5 fd99d3bb4a Deep CFR self-play anchor safe 512x3 2x updates 10000 iter config 및 관련 변경 
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
 2026-05-07 09:14:23 +09:00
coolguy c779621823 Deep CFR pure self-play 512x3 2x updates config 추가 2026-05-07 07:55:05 +09:00
coolguy 55f4ae89a4 Deep CFR 512x3 LCFR config 추가 2026-05-07 07:12:39 +09:00
coolguy 6d84745daa Limit Deep CFR traversal futures in flight 2026-05-07 07:11:45 +09:00
coolguy ccf7f825f7 Deep CFR 512x3 2x updates config 추가 2026-05-07 07:11:02 +09:00
coolguy 768c071e90 Deep CFR 512x3 unbounded config 추가 2026-05-07 07:05:11 +09:00
coolguy 4712a9af89 Deep CFR LCFR DCFR loss weighting 추가 2026-05-07 06:30:48 +09:00
coolguy e1a5185d4d Deep CFR 아이디어와 분석 플롯 정리 2026-05-07 06:21:19 +09:00
coolguy 080bff517e Deep CFR regret fallback audit metrics 추가 2026-05-07 05:23:23 +09:00
coolguy 690e086738 Improve Deep CFR analysis dashboards 2026-05-07 04:58:27 +09:00
coolguy 4ec784217b Deep CFR legacy 학습 dynamics 정렬 2026-05-07 04:20:11 +09:00
coolguy 6433081ed2 Deep CFR 분석 대시보드 정리 2026-05-07 04:05:31 +09:00
coolguy f5a72aeaec 프로젝트 운영 가이드 추가 2026-05-07 04:04:10 +09:00
coolguy 5fa4bd65ef Deep CFR 무제한 학습 config 추가 2026-05-07 03:52:59 +09:00
coolguy 148be6e9a0 Deep CFR evaluation 배칭 및 병렬화 추가 2026-05-07 03:42:00 +09:00
coolguy 54347e1e7f Deep CFR evaluation 프로파일링 메트릭 추가 2026-05-07 03:10:19 +09:00
coolguy 9acf9ed261 Deep CFR advantage memory를 player별로 분리 2026-05-07 02:59:03 +09:00
coolguy e411ea4a15 Deep CFR 프로파일링 메트릭 추가 2026-05-07 02:50:35 +09:00
coolguy b5b4f97d41 Deep CFR slot-aware encoding NaN 수정 2026-05-07 02:32:24 +09:00
coolguy ece82fc310 Deep CFR traversal을 Cython 엔진으로 교체 2026-05-07 02:25:33 +09:00
coolguy a76e8fd716 Deep CFR 성능 traversal gap 문서화 2026-05-07 02:12:14 +09:00
coolguy cd3f7cea3b Add test coverage notes 2026-05-07 02:11:16 +09:00
coolguy facd6eb36a Deep CFR traversal 재귀 한도 보강 2026-05-07 02:02:56 +09:00
coolguy 44a96f5b4c Deep CFR checkpoint CLI override 추가 2026-05-07 01:59:16 +09:00
coolguy fc4f0ddfd8 Deep CFR resume 동작 보강 2026-05-07 01:55:10 +09:00
coolguy 1645d22e87 Deep CFR 콘솔 트래킹 출력 정리 2026-05-07 01:47:54 +09:00
coolguy 1420ab76bd Deep CFR run tracking 추상화 2026-05-07 01:44:15 +09:00
coolguy 1b6d98ceeb Deep CFR traversal 운영 로그 보강 2026-05-07 01:23:26 +09:00
coolguy d29b3d60bb Deep CFR 재현 config 이름 정리 2026-05-07 01:15:34 +09:00
coolguy df8f979ce4 Deep CFR 재현 config 실행 보강 2026-05-07 01:12:09 +09:00
coolguy bbf8950c3a Deep CFR 재현 config run dir 정리 2026-05-07 01:05:23 +09:00
coolguy 312cbd3949 Deep CFR evaluation 진단 metric 추가 2026-05-07 01:03:09 +09:00
coolguy 7ef7e5b927 Deep CFR endpoint depth metrics 보강 2026-05-07 00:54:16 +09:00
coolguy 95d0660b0b Deep CFR playability encoding 추가 2026-05-07 00:52:28 +09:00
coolguy 9bcc88c1be Deep CFR legacy 재현 config 기반 추가 2026-05-07 00:46:09 +09:00
coolguy 898f927cb2 Deep CFR legacy 실험 재현 계획 문서화 2026-05-07 00:41:19 +09:00
coolguy f593a6d910 Deep CFR YAML config 추가 2026-05-07 00:30:42 +09:00
coolguy d86e534ba9 Deep CFR status 문서 갱신 2026-05-07 00:14:51 +09:00
coolguy b71f4b95be Deep CFR policy gradient fine-tuning 추가 2026-05-07 00:13:53 +09:00
coolguy 647baa7d6d Deep CFR imitation pretraining 추가 2026-05-07 00:12:41 +09:00
coolguy 8f54415832 Deep CFR multiprocessing benchmark 보강 2026-05-07 00:11:01 +09:00
coolguy 5555e781af Deep CFR weighted self-play league 추가 2026-05-07 00:09:36 +09:00
coolguy 573b59545f Deep CFR legacy gap 문서 정리 2026-05-07 00:02:25 +09:00
coolguy 46d841cf11 Deep CFR self-play league 추가 2026-05-07 00:01:19 +09:00
coolguy a5bd5eeb7e Deep CFR traversal multiprocessing과 benchmark 추가 2026-05-06 23:59:01 +09:00
coolguy 76833109dc Deep CFR 로컬 metrics logging 추가 2026-05-06 23:54:52 +09:00
coolguy fc5b3d9bc8 Deep CFR checkpoint eval CLI 추가 2026-05-06 23:52:50 +09:00