From 63962c331ceab838788610e8d084785477af9a4d Mon Sep 17 00:00:00 2001
From: mlerik <baerenjesus@gmail.com>
Date: Mon, 15 Jul 2019 16:53:34 +0000
Subject: [PATCH] Update Multi_Agent_Training_Intro.md

---
 torch_training/Multi_Agent_Training_Intro.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/torch_training/Multi_Agent_Training_Intro.md b/torch_training/Multi_Agent_Training_Intro.md
index f9aaa21..569d7f0 100644
--- a/torch_training/Multi_Agent_Training_Intro.md
+++ b/torch_training/Multi_Agent_Training_Intro.md
@@ -245,9 +245,9 @@ We now use the normalized `agent_obs` for our training loop:
 
 Running the `multi_agent_training.py` file trains a simple agent to navigate to any random target within the railway network. After running you should see a learning curve similiar to this one:
 
-![Learning_curve](https://i.imgur.com/yVGXpUy.png)
+*Learning curve provided soon*
 
 and the agent behavior should look like this:
 
-![Single_Agent_Navigation](https://i.imgur.com/t5ULr4L.gif)
+*Gif provided soon*
 
-- 
GitLab