From 63acef72a4446de1148fc0d15a5d7d7f4300b0f9 Mon Sep 17 00:00:00 2001
From: Johnny He <269401927@qq.com>
Date: Fri, 16 Nov 2018 17:30:31 +0800
Subject: [PATCH] Update readme.md

---
 DQN/readme.md | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/DQN/readme.md b/DQN/readme.md
index 30aaf83..8008a4c 100644
--- a/DQN/readme.md
+++ b/DQN/readme.md
@@ -8,3 +8,7 @@
 ## Tips for MountainCar-v0 env:
 
 This is very sparse for MountainCar-v0, it is 0 at the beginning, only when the top of the mountain is 1, there is a reward. This leads to the fact that if the sample to the top of the mountain is not taken during training, basically the train will not come out. So you can change the reward, for example, to change to the current position of the Car is positively related. Of course, there is a more advanced approach to inverse reinforcement learning (using GAN).
+
+![value_loss](DQN/value_loss.jpg)   
+![value_loss](DQN/finish_episode.jpg) 
+This is value loss for DQN, We can see that the loss increaded to 1e13 however, the network work well. This is because the training is going on, the target_net and act_net are very different, so the calculated loss becomes very large. The previous loss was small because the reward was very sparse, resulting in a small update of the two networks.