diff --git a/crates/ml/src/hyperopt/adapters/dqn.rs b/crates/ml/src/hyperopt/adapters/dqn.rs
index 9799b35bc..35a049315 100644
--- a/crates/ml/src/hyperopt/adapters/dqn.rs
+++ b/crates/ml/src/hyperopt/adapters/dqn.rs
@@ -878,7 +878,10 @@ impl DQNTrainer {
             let mut preload_hyperparams = DQNHyperparameters::default();
             preload_hyperparams.mbp10_data_dir = self.mbp10_data_dir.clone().unwrap_or_default();
             preload_hyperparams.trades_data_dir = self.trades_data_dir.clone().unwrap_or_default();
-            preload_hyperparams.buffer_size = 1;
+            // Buffer size must be >= batch_size for GPU PER allocation.
+            // Preload doesn't train — just loads data — but the trainer
+            // constructor still creates a PER buffer.
+            preload_hyperparams.buffer_size = preload_hyperparams.batch_size.max(1024);
             let mut loader = InternalDQNTrainer::new_with_device(preload_hyperparams, self.device.clone())
                 .map_err(|e| MLError::TrainingError(format!("Failed to create data loader: {e}")))?;