From db2d948f9330e97caf44e5c8a60b76ff94682b69 Mon Sep 17 00:00:00 2001
From: vanking <128895735+vanking20000918@users.noreply.github.com>
Date: Tue, 3 Feb 2026 10:34:20 +0800
Subject: [PATCH] Update train_gated_ppo.py

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

diff --git a/train_gated_ppo.py b/train_gated_ppo.py
index 6aa966b..58135c2 100644
--- a/train_gated_ppo.py
+++ b/train_gated_ppo.py
@@ -166,7 +166,7 @@ def ppo_train_epoch(epoch, loader, iters, old_actor_model, ref_model, actor_sche
 
         # 修改部分：添加门控
         ratio = torch.exp(actor_logp - old_logp)  # [B]
-        ratio = ratio * torch.sigmoid(0.5 * ratio)
+        ratio = ratio * torch.sigmoid(0.1 * ratio)
 
         surr1 = ratio * advantages  # [B]
         surr2 = torch.clamp(ratio, 1.0 - args.clip_epsilon, 1.0 + args.clip_epsilon) * advantages  # [B]