diff --git a/tools/training_runner/training.env b/tools/training_runner/training.env
index 40e1c84..c27d431 100644
--- a/tools/training_runner/training.env
+++ b/tools/training_runner/training.env
@@ -4,7 +4,7 @@ PPOB_LOG_FILE=/home/davide/Projects/SirRoboGarage/tools/training_runner/logs/fir
 PPOB_LR=1e-4
 PPOB_UPDATE_INTERVAL=10
 PPOB_CLIP_EPSILON=0.2
-PPOB_ENTROPY_COEFF=0.001
+PPOB_ENTROPY_COEFF=0.0
 PPOB_VALUE_LOSS_COEFF=0.5
 PPOB_MAX_GRAD_NORM=0.5
 PPOB_GAMMA=0.99
@@ -12,7 +12,7 @@ PPOB_LAM=0.95
 PPOB_EPOCHS=4
 PPOB_MINI_BATCH_SIZE=64
 PPOB_LOG_STD_FLOOR=-3.0
-PPOB_LOG_STD_CEILING=-0.5
+PPOB_LOG_STD_CEILING=-1.0
 PPOB_INITIAL_LOG_STD=-0.5
 
 # PPOB_EVAL_ONLY=1 → freeze training (pure evaluation)
diff --git a/tools/warm_start.py b/tools/warm_start.py
index 7c06f11..8ea1d00 100644
--- a/tools/warm_start.py
+++ b/tools/warm_start.py
@@ -37,10 +37,10 @@ for name in unchanged:
     np.save(DST / f"{name}.npy", data)
     print(f"  {name}: {data.shape} copied")
 
-# Initialize log_std to -1.0 (std ≈ 0.37) — snapshot values (2.27–4.68) are too high for fine-tuning
-log_std = np.full(6, -1.0, dtype=np.float32)
+# Initialize log_std to -2.0 (std ≈ 0.135) — tighter than -1.0, proven workable
+log_std = np.full(6, -2.0, dtype=np.float32)
 np.save(DST / "log_std.npy", log_std)
-print(f"  log_std: initialized to -1.0 (std≈0.37), shape={log_std.shape}")
+print(f"  log_std: initialized to -2.0 (std≈0.135), shape={log_std.shape}")
 
 # Copy unchanged Adam moments (all except w1, which were handled above)
 unchanged_adam = [