diff --git a/crates/ml/src/trainers/dqn/trainer/training_loop.rs b/crates/ml/src/trainers/dqn/trainer/training_loop.rs
index 16a65aaa2..e38189078 100644
--- a/crates/ml/src/trainers/dqn/trainer/training_loop.rs
+++ b/crates/ml/src/trainers/dqn/trainer/training_loop.rs
@@ -1473,10 +1473,10 @@ impl DQNTrainer {
             }
         }
 
+        // Acquire write lock ONCE for the entire training loop — not per-step.
+        // Per-step lock acquisition was burning 696s/epoch due to async yield overhead.
+        let mut agent = self.agent.write().await;
         for _step in 0..num_training_steps {
-            // Single write lock for both sample + fused step — eliminates
-            // read→write lock cycling overhead (~43ms per step from contention).
-            let mut agent = self.agent.write().await;
 
             let sample_start = std::time::Instant::now();
             {