diff --git a/crates/ml/src/trainers/dqn/trainer.rs b/crates/ml/src/trainers/dqn/trainer.rs
index bbc46d08f..a06c22b12 100644
--- a/crates/ml/src/trainers/dqn/trainer.rs
+++ b/crates/ml/src/trainers/dqn/trainer.rs
@@ -2659,6 +2659,17 @@ impl DQNTrainer {
                     train_step_count as f64 / epoch_duration.as_secs_f64(),
                 );
             }
+            // Tier 1: RL diagnostics + training health
+            training_metrics::set_q_value_stats("dqn", "current", q_mean, q_max);
+            training_metrics::set_gradient_norm("dqn", "current", avg_grad_norm);
+            training_metrics::set_epoch_duration("dqn", "current", epoch_duration.as_secs_f64());
+            training_metrics::set_learning_rate("dqn", "current", current_lr);
+            {
+                let agent = self.agent.read().await;
+                if let Ok(buf_size) = agent.get_replay_buffer_size() {
+                    training_metrics::set_replay_buffer_size("dqn", "current", buf_size as f64);
+                }
+            }
 
             // WAVE 9-11 PRODUCTION: Track action diversity per epoch
             // Calculate active actions (used >0.5% of the time)