diff --git a/crates/ml-alpha/src/trainer/integrated.rs b/crates/ml-alpha/src/trainer/integrated.rs
index 2b335d02c..1043884da 100644
--- a/crates/ml-alpha/src/trainer/integrated.rs
+++ b/crates/ml-alpha/src/trainer/integrated.rs
@@ -2379,9 +2379,27 @@ impl IntegratedTrainer {
             }
         }
 
-        // Update ISV[423] MEAN_ABS_PNL_EMA from |reward| over closed
-        // trades (dones_d gating). R5 controllers consume this on
-        // their next per-step launch below.
+        // Update ISV[423] MEAN_ABS_PNL_EMA from |reward| over ALL
+        // non-zero reward events (NOT just trade closes).
+        //
+        // Originally gated on dones_d so only closed-trade realized
+        // PnL contributed to the EMA. Cluster smoke `alpha-rl-9cbpj`
+        // diag revealed that 170 of 266 non-zero reward events occur
+        // on non-done steps (mid-trade PnL deltas from trail-stop
+        // adjustments / mark-to-market / partial fills). These
+        // mid-trade swings can be 2-3× larger than realized close
+        // PnL — invisible to a done-gated EMA, they end up scaled
+        // by `reward_scale = 1/mean_abs_pnl_close` which is calibrated
+        // for the smaller magnitude. Result: V regression target
+        // spikes ×50-100 on volatile mid-trade steps (l_v=3,456
+        // observed at step 590 with raw $2,390 PnL × scale=0.0011).
+        //
+        // The kernel's "done" parameter is really a generic gate
+        // tested as `d >= 0.5`. Passing reward_abs_d as the gate
+        // gives "gate on |reward| ≥ 0.5" (= "non-zero reward" for
+        // any practical magnitude in dollars) — exactly the
+        // semantics we want. Zero-reward steps stay excluded so the
+        // EMA isn't biased toward zero on idle steps.
         {
             let cfg = LaunchConfig {
                 grid_dim: (1, 1, 1),
@@ -2396,7 +2414,7 @@ impl IntegratedTrainer {
                 .arg(&slot_i)
                 .arg(&alpha)
                 .arg(&self.reward_abs_d)
-                .arg(&self.dones_d)
+                .arg(&self.reward_abs_d)  // gate on |reward|>0, not just on dones
                 .arg(&b_size_i);
             unsafe {
                 launch