From 459215b7d84d01e64cfd352a971cf62d8e2a17fd Mon Sep 17 00:00:00 2001
From: Codex <codex@localhost>
Date: Mon, 13 Jul 2026 03:25:55 +0200
Subject: [PATCH] malkhut(fix): wire workers into CMA training loop

CMAESTrainer.train() now accepts workers parameter and passes it to
evaluate_candidate(), enabling parallel episode evaluation during
actual training (not just in tests/benchmarks).

Benchmark result: ProcessPoolExecutor is optimal (4.76x speedup).
Ray is slower (0.36x) due to head init + plasma overhead for 90 scenarios.
---
 MALKHUT/malkhut/training/cma_trainer.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/MALKHUT/malkhut/training/cma_trainer.py b/MALKHUT/malkhut/training/cma_trainer.py
index 8f695c8..e176cc0 100644
--- a/MALKHUT/malkhut/training/cma_trainer.py
+++ b/MALKHUT/malkhut/training/cma_trainer.py
@@ -1237,11 +1237,13 @@ class CMAESTrainer:
         evaluator: PolicyEvaluator,
         pool: SelfPlayPool,
         store: Optional[MalkhutCHStore] = None,
+        workers: int = 0,
     ) -> None:
         self.codec = codec
         self.evaluator = evaluator
         self.pool = pool
         self.store = store
+        self._workers = workers
 
     def train(
         self,
@@ -1283,7 +1285,7 @@ class CMAESTrainer:
                 candidate = self.codec.decode(x, version=f"cma_{time.time_ns()}_{evals}")
                 score, results = self.evaluator.evaluate_candidate(
                     params=candidate, scenarios=scenarios, rng_seed=seed + evals,
-                    planner_type=planner_type,
+                    planner_type=planner_type, workers=self._workers,
                 )
                 perf_vec = PolicyEvaluator.performance_vector(results)
                 snap = PolicySnapshot(