Add training.value_loss_weight (default 1.0) for value loss reweighting

Diagnosis: mcts/value_prediction_error stuck at 300-1000 (RMSE ~22 on score
range ±100), while loss/value stays at 0.05 because the loss divides
prediction and target by value_scale=100 (so MSE / 10000). Net effect: the
value head receives a tiny gradient relative to the policy head's
~1.75 cross-entropy loss, so it never learns to predict score scale well.

This adds a config knob to multiply the normalized value loss without
re-engineering the loss formula. value_loss_weight=50 recovers the raw
MSE magnitude (~2.5 vs policy loss ~1.75), giving the value head
comparable gradient signal.

src/coolrl_lost_cities/games/classic/ismcts/config.py

@@ -62,6 +62,11 @@ class TrainingConfig(StrictModel):
     interleave_max_batch: int = 64
     num_workers: int = 1
     worker_device: str = "cpu"
+    # Multiplier on the value-head MSE loss (already normalized by value_scale**2).
+    # Default 1.0 keeps current behavior; raising it (e.g. 50-100) makes the value
+    # head learn faster relative to policy loss. Useful when value_prediction_error
+    # is large but loss/value is tiny because of the normalization.
+    value_loss_weight: float = 1.0
 
     @field_validator(
         "games_per_iter",

src/coolrl_lost_cities/games/classic/ismcts/trainer.py

@@ -261,7 +261,8 @@ class IsMctsTrainer:
         policy_loss = -(pi * log_probs).sum(dim=-1).mean()
         v_scale = float(self.network.value_scale)
         value_loss = nn.functional.mse_loss(value_pred / v_scale, value_target / v_scale)
-        loss = policy_loss + value_loss
+        value_weight = float(self.config.training.value_loss_weight)
+        loss = policy_loss + value_weight * value_loss
         self.optimizer.zero_grad(set_to_none=True)
         loss.backward()
         if self.config.optimization.grad_clip > 0: