From 353c8d81ab9325a20ab5d0bb7f7cf25cebf846f2 Mon Sep 17 00:00:00 2001
From: jgrusewski <jgrusewski@localhost>
Date: Mon, 20 Apr 2026 07:53:29 +0200
Subject: [PATCH] =?UTF-8?q?tune:=20revert=20LR=202e-5=20=E2=86=92=201e-5?=
 =?UTF-8?q?=20=E2=80=94=20too=20aggressive=20with=20architectural=20change?=
 =?UTF-8?q?s?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

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 | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/config/training/dqn-production.toml b/config/training/dqn-production.toml
index 7f8c4967a..5350f94e4 100644
--- a/config/training/dqn-production.toml
+++ b/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