From f20b1aa22201dc9870cedf74be76caa06a0eeedd Mon Sep 17 00:00:00 2001 From: Mahdi Dibaiee Date: Sun, 2 Apr 2017 16:51:57 +0430 Subject: [PATCH] gifs --- README.md | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 88154eb..6fba5b9 100644 --- a/README.md +++ b/README.md @@ -8,9 +8,8 @@ Training process is pretty fast as there is no backpropagation, and is not very Here is a demonstration of the model before training and after ~3000 iterations (less than an hour of training): -Before training: - -![before training](/demo/flappy-lose.gif) +[Before training](/demo/flappy-lose.gif) +[After training:](/demo/flappy-success.gif) ![after training](/demo/flappy-success.gif) For each frame the bird stays alive, +1 score is given to him. For each wall he passes, +10 score is given.