diff --git a/crates/ml/src/trainers/dqn/smoke_tests/mod.rs b/crates/ml/src/trainers/dqn/smoke_tests/mod.rs
index 12a29580d..ae02f7b8f 100644
--- a/crates/ml/src/trainers/dqn/smoke_tests/mod.rs
+++ b/crates/ml/src/trainers/dqn/smoke_tests/mod.rs
@@ -17,7 +17,7 @@ mod hyperopt;
 #[cfg(test)]
 mod regression;
 #[cfg(test)]
-pub mod reward_v8;
+mod reward_v8;
 #[cfg(test)]
 mod generalization;
 #[cfg(test)]
diff --git a/crates/ml/src/trainers/dqn/trainer/training_loop.rs b/crates/ml/src/trainers/dqn/trainer/training_loop.rs
index 67e306eb3..6bba5e18a 100644
--- a/crates/ml/src/trainers/dqn/trainer/training_loop.rs
+++ b/crates/ml/src/trainers/dqn/trainer/training_loop.rs
@@ -1821,7 +1821,28 @@ impl DQNTrainer {
                 .unwrap_or(1.0);
 
             let grad_norm = avg_grad.abs();
-            let ens_disagreement = 0.1f32; // placeholder — D6/N6 task will replace with real ensemble pairwise Q-gap
+
+            // Ensemble disagreement: dispersion across the 4 per-branch Q-gaps as a
+            // proxy for true per-head ensemble disagreement (per-head Q readback isn't
+            // wired in this codebase). When all branches collapse to similar Q-gap, the
+            // range shrinks → low disagreement → D6/N6 oracle score rises. When
+            // branches preserve diverse Q-gaps (healthy), the range is wider. Maps
+            // directly into the smoothstep(0.01, 0.1) thresholds in from_raw and the
+            // D6 oracle's own smoothstep with the same window.
+            let ens_disagreement = if let Some(ref fused) = self.fused_ctx {
+                let gaps = fused.per_branch_q_gap_ema();
+                let mut gmin = f32::INFINITY;
+                let mut gmax = f32::NEG_INFINITY;
+                for &g in &gaps {
+                    if g.is_finite() {
+                        if g < gmin { gmin = g; }
+                        if g > gmax { gmax = g; }
+                    }
+                }
+                if gmin.is_finite() && gmax.is_finite() { (gmax - gmin).max(0.0) } else { 0.1 }
+            } else {
+                0.1
+            };
 
             // Update EMAs.
             self.health_ema.update(q_gap_signal, q_var_signal, grad_norm);
@@ -2082,8 +2103,8 @@ impl DQNTrainer {
                 self.learning_health.components.spectral_gap_norm,
                 self.last_cql_alpha_eff.unwrap_or(0.0),
                 self.last_iqn_budget_eff.unwrap_or(0.40),
-                self.last_cql_budget_eff.unwrap_or(0.10),
-                self.last_c51_budget_eff.unwrap_or(0.45),
+                self.last_cql_budget_eff.unwrap_or(0.00),
+                self.last_c51_budget_eff.unwrap_or(0.55),
                 self.last_tau_eff.unwrap_or(0.005),
                 self.last_sarsa_tau_factor.unwrap_or(1.0),
                 self.last_gamma_eff.unwrap_or(0.99),