coolguyandCodex 7c20d53103 Measure traversal policy boundary cost ...

Add a microbench that separates game/encoding overhead, single-request policy boundary overhead, and batched PyTorch forward lower bounds. Record CPU/CUDA results and link the finding from the Julia port evaluation.

Co-Authored-By: Codex <codex@openai.com>

2026-05-07 22:02:46 +09:00

..

deep-cfr-architecture.md

Add Deep CFR research notes derived from archive

2026-05-07 20:45:15 +09:00

deep-cfr-v0-feature-parity.md

Add Deep CFR research notes derived from archive

2026-05-07 20:45:15 +09:00

julia_port_evaluation.md

Measure traversal policy boundary cost

2026-05-07 22:02:46 +09:00

lost_cities_selectivity.md

Add Lost Cities selectivity research notes (4-model analysis)

2026-05-07 20:58:09 +09:00

opponent-policy-network-divergence.md

Add Deep CFR research notes derived from archive

2026-05-07 20:45:15 +09:00

optimization_sequencing.md

Document optimization lever sequencing rationale

2026-05-07 21:35:52 +09:00

outcome-sampling-target.md

Add Deep CFR research notes derived from archive

2026-05-07 20:45:15 +09:00

regret-matching-fallback.md

Add Deep CFR research notes derived from archive

2026-05-07 20:45:15 +09:00

strategy-memory-location.md

Validate strategy-memory flags under external sampling

2026-05-07 20:56:57 +09:00