tune: revert LR 2e-5 → 1e-5 — too aggressive with architectural changes

Linear scaling rule (2x batch → 2x LR) doesn't hold for DQN+PER with
major architectural changes (Hold action, OFI embed, wider attention).
The model needs stability to learn the new action space, not speed.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

config/training/dqn-production.toml

@@ -14,7 +14,7 @@
 [training]
 epochs = 200
 batch_size = 16384
-learning_rate = 2e-5
+learning_rate = 1e-5
 gamma = 0.99
 weight_decay = 0.0001
 adam_epsilon = 1e-8