Commit Graph
4 Commits
Author SHA1 Message Date
coolguy fe01704b60 Add deterministic Deep CFR traversal mode 2026-05-08 16:09:03 +09:00
coolguyandCodex 09bbe7ccf7 Make interleaved traversal the default
Co-Authored-By: Codex <codex@openai.com>
2026-05-07 23:21:15 +09:00
coolguyandClaude Opus 4.7 a7ab94e096 Add batched traversal inference server (Option A) behind opt-in flag
Implements the central inference server pattern: a dedicated GPU
process owns advantage/strategy/league networks, batches policy
requests across traversal workers via shared-memory tensor pool, and
returns logits. Workers route forward calls through InferenceClient /
NetworkProxy when traversal.inference_backend == "server".

Default remains traversal.inference_backend: local. The server
backend regresses iter time ~3.8× on the inspected default config
(small-model dispatch + sync-blocking traversal capping realized
batch at ~num_workers=8 instead of the bs=64-256 needed to amortize
IPC overhead). Keeping the implementation behind the flag lets us
re-enable when (a) model size grows, (b) per-worker interleaved
traversal lands, or (c) eval becomes dominant — see
docs/performance.md "Option A Bench Result and Structural Ceiling"
for the full diagnosis.

Plumbing included:
- inference_buffers.py: shared-memory tensor pool with slot
  management.
- inference_client.py: per-worker client + NetworkProxy adapter for
  the existing traversal.pyx call sites.
- inference_server.py: spawn-context server process with
  batch-window aggregation, weight sync, shutdown sentinel.
- bench_inference_backend.py: A/B between local and server backends
  with eval/checkpoint disabled.
- test_inference_server.py: round-trip and integration tests.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-07 20:05:16 +09:00
coolguyandClaude Opus 4.7 618d5f8167 Promote avg-strategy 1000iter to default.yaml; archive other configs
The avg-strategy 1000iter file (with the recent +traversals/+LR/+LCFR
changes) is the canonical "best-known" config. Renamed it to
default.yaml so users start from a single, obvious entry point and
override one field per ablation via --set. Other 12 configs moved to
configs/archive/ — kept for historical reproduction, not for active use.

- configs/deep_cfr/{default.yaml, smoke.yaml} are the only active configs
- experiment_name shortened to "deep-cfr-default" (was a long mouthful)
- AGENTS.md examples and Project Layout section rewritten around
  default.yaml; ablation example shows the override-one-field pattern
- Tests pointed at the archived slot-playability config for the legacy
  reproduction assertions

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-07 17:09:20 +09:00