diff --git a/crates/ml/src/trainers/dqn/trainer/training_loop.rs b/crates/ml/src/trainers/dqn/trainer/training_loop.rs
index bc16def12..5de0b01e8 100644
--- a/crates/ml/src/trainers/dqn/trainer/training_loop.rs
+++ b/crates/ml/src/trainers/dqn/trainer/training_loop.rs
@@ -477,8 +477,23 @@ impl DQNTrainer {
                 let num_atoms = self.hyperparams.num_atoms;
                 match collector.compute_reward_quantiles(count, num_atoms) {
                     Ok(quantiles) => {
+                        // Raw reward quantiles are unbounded — a single extreme
+                        // PnL sample from the environment becomes `atom_positions[50]`,
+                        // and the C51 expected-value read `Q = Σ prob × atom_pos`
+                        // inherits that magnitude. Observed on L40S: epoch 1 Q in
+                        // [0, 6], epoch 2 Q at ±333k — the tail of the sorted
+                        // reward distribution from the first experience buffer.
+                        // Clamp to the configured `[v_min, v_max]` so warm-start
+                        // respects the C51 support bounds that every downstream
+                        // path (loss projection, eval_v_range, IQL support) assumes.
+                        let v_min = self.hyperparams.v_min as f32;
+                        let v_max = self.hyperparams.v_max as f32;
+                        let clamped_quantiles: Vec<f32> = quantiles
+                            .iter()
+                            .map(|&q| q.clamp(v_min, v_max))
+                            .collect();
                         if let Some(ref mut fused) = self.fused_ctx {
-                            if let Err(e) = fused.warm_start_atom_positions(&quantiles) {
+                            if let Err(e) = fused.warm_start_atom_positions(&clamped_quantiles) {
                                 warn!("C51 atom warm-start failed (non-fatal): {e}");
                             }
                         }