diff --git a/crates/ml/src/trainers/dqn/fused_training.rs b/crates/ml/src/trainers/dqn/fused_training.rs
index 2ff145c58..74df8bb36 100644
--- a/crates/ml/src/trainers/dqn/fused_training.rs
+++ b/crates/ml/src/trainers/dqn/fused_training.rs
@@ -1001,6 +1001,13 @@ impl FusedTrainingCtx {
         }
         self.pending_vaccine_batch = None;
 
+        // ── Adaptive IQN lambda: read loss OUTSIDE graph capture ─────────
+        if let Some(ref iqn) = self.gpu_iqn {
+            if let Ok(loss) = iqn.read_total_loss() {
+                self.trainer.update_iqn_readiness(loss);
+            }
+        }
+
         // ── Clip grad_buf L2 norm BEFORE Adam (outside graph) ───────────
         // Root cause: backward weight gradient dW = activation^T × d_output.
         // Spectral norm bounds W, IS-weight clamp bounds d_logits (~2.0),
@@ -1272,11 +1279,6 @@ impl FusedTrainingCtx {
                 dqn_actions, dqn_rewards, dqn_dones,
             ) {
                 Ok(_) => {
-                    // Update adaptive IQN lambda from current loss
-                    if let Ok(loss) = iqn.read_total_loss() {
-                        self.trainer.update_iqn_readiness(loss);
-                    }
-
                     let d_h_s2_ptr = iqn.d_h_s2_raw_ptr();
                     self.trainer.apply_iqn_trunk_gradient(
                         d_h_s2_ptr, &mut self.online_dueling,