diff --git a/crates/ml-alpha/examples/alpha_rl_train.rs b/crates/ml-alpha/examples/alpha_rl_train.rs
index 8ebaa8f98..1b601a33b 100644
--- a/crates/ml-alpha/examples/alpha_rl_train.rs
+++ b/crates/ml-alpha/examples/alpha_rl_train.rs
@@ -39,10 +39,15 @@ use ml_alpha::data::loader::{
 use ml_alpha::heads::HORIZONS;
 use ml_alpha::rl::isv_slots::{
     RL_ADVANTAGE_VAR_RATIO_EMA_INDEX, RL_ENTROPY_COEF_INDEX, RL_ENTROPY_OBSERVED_EMA_INDEX,
-    RL_GAMMA_INDEX, RL_KL_PI_EMA_INDEX, RL_LR_AUX_INDEX, RL_LR_BCE_INDEX, RL_LR_PI_INDEX,
-    RL_LR_Q_INDEX, RL_LR_V_INDEX, RL_MEAN_ABS_PNL_EMA_INDEX, RL_MEAN_TRADE_DURATION_EMA_INDEX,
-    RL_N_ROLLOUT_STEPS_INDEX, RL_PER_ALPHA_INDEX, RL_PPO_CLIP_INDEX, RL_Q_DIVERGENCE_EMA_INDEX,
-    RL_REWARD_SCALE_INDEX, RL_TARGET_TAU_INDEX, RL_TD_KURTOSIS_EMA_INDEX,
+    RL_GAMMA_INDEX, RL_KL_PI_EMA_INDEX, RL_LR_AUX_INDEX, RL_LR_BCE_INDEX, RL_LR_PI_BEST_LOSS_INDEX,
+    RL_LR_PI_INDEX, RL_LR_PI_LOSS_EMA_INDEX, RL_LR_PI_STEPS_SINCE_BEST_INDEX,
+    RL_LR_Q_BEST_LOSS_INDEX, RL_LR_Q_INDEX, RL_LR_Q_LOSS_EMA_INDEX,
+    RL_LR_Q_STEPS_SINCE_BEST_INDEX, RL_LR_V_BEST_LOSS_INDEX, RL_LR_V_INDEX,
+    RL_LR_V_LOSS_EMA_INDEX, RL_LR_V_STEPS_SINCE_BEST_INDEX, RL_MEAN_ABS_PNL_EMA_INDEX,
+    RL_MEAN_TRADE_DURATION_EMA_INDEX, RL_N_ROLLOUT_STEPS_INDEX, RL_PER_ALPHA_INDEX,
+    RL_PI_GRAD_NORM_EMA_INDEX, RL_PPO_CLIP_INDEX, RL_Q_DIVERGENCE_EMA_INDEX,
+    RL_Q_GRAD_NORM_EMA_INDEX, RL_REWARD_SCALE_INDEX, RL_TARGET_TAU_INDEX, RL_TD_KURTOSIS_EMA_INDEX,
+    RL_V_GRAD_NORM_EMA_INDEX,
 };
 use ml_alpha::trainer::integrated::{
     read_slice_d_pub, read_slice_i32_d_pub, IntegratedStepStats, IntegratedTrainer,
@@ -506,6 +511,31 @@ fn main() -> Result<()> {
                 "td_kurtosis":         isv[RL_TD_KURTOSIS_EMA_INDEX],
                 "mean_abs_pnl":        isv[RL_MEAN_ABS_PNL_EMA_INDEX],
             },
+            // Grad-norm EMAs (diagnostic — no longer drive the LR
+            // controller as of commit 042de99e6 but still useful to
+            // correlate with plateau-decay events).
+            "grad_norm_ema": {
+                "q":  isv[RL_Q_GRAD_NORM_EMA_INDEX],
+                "pi": isv[RL_PI_GRAD_NORM_EMA_INDEX],
+                "v":  isv[RL_V_GRAD_NORM_EMA_INDEX],
+            },
+            // Plateau-decay LR controller state (per head). loss_ema is
+            // the controller's internal slow EMA at α=0.05; best is the
+            // lowest loss_ema observed so far; steps_since_best is the
+            // staleness counter that fires LR halving at PLATEAU_PATIENCE
+            // (1000). Confirms whether the controller is seeing plateaus
+            // and decaying for the right reason.
+            "lr_plateau": {
+                "q":  { "loss_ema": isv[RL_LR_Q_LOSS_EMA_INDEX],
+                         "best":     isv[RL_LR_Q_BEST_LOSS_INDEX],
+                         "stale":    isv[RL_LR_Q_STEPS_SINCE_BEST_INDEX] },
+                "pi": { "loss_ema": isv[RL_LR_PI_LOSS_EMA_INDEX],
+                         "best":     isv[RL_LR_PI_BEST_LOSS_INDEX],
+                         "stale":    isv[RL_LR_PI_STEPS_SINCE_BEST_INDEX] },
+                "v":  { "loss_ema": isv[RL_LR_V_LOSS_EMA_INDEX],
+                         "best":     isv[RL_LR_V_BEST_LOSS_INDEX],
+                         "stale":    isv[RL_LR_V_STEPS_SINCE_BEST_INDEX] },
+            },
             "replay_len": trainer.replay.len(),
             "rewards": {
                 "sum":     reward_sum,