thereadme/flappy-es
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

style

Browse Source
This commit is contained in:
Mahdi Dibaiee 2017-04-02 16:55:06 +04:30
parent 8ed8b14c76
commit ab55f649c5
1 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -6,13 +6,11 @@ After reading [Evolution Strategies as a Scalable Alternative to Reinforcement L
The model learns to play very well after ~1500 iterations, but not completely flawless and it usually loses in difficult cases (high difference between two wall entrances). The model learns to play very well after ~1500 iterations, but not completely flawless and it usually loses in difficult cases (high difference between two wall entrances).
Training process is pretty fast as there is no backpropagation, and is not very costy in terms of memory as there is no need to record actions as in policy gradients. Training process is pretty fast as there is no backpropagation, and is not very costy in terms of memory as there is no need to record actions as in policy gradients.
Here is a demonstration of the model before training and after ~3000 iterations (less than an hour of training): Here is a demonstration of the model after ~1500 iterations (less than an hour of training):
[After training:](/demo/flappy-success.gif)
![after training](/demo/flappy-success.gif) ![after training](/demo/flappy-success.gif)
[Before training](/demo/flappy-lose.gif) also see: [Before training](/demo/flappy-lose.gif)
For each frame the bird stays alive, +1 score is given to him. For each wall he passes, +10 score is given. For each frame the bird stays alive, +1 score is given to him. For each wall he passes, +10 score is given.