From 44108284e34490889b4fbf81c58f269cc17e56f2 Mon Sep 17 00:00:00 2001 From: Mahdi Dibaiee Date: Fri, 7 Dec 2018 10:42:26 +0330 Subject: [PATCH] feat(charts): draw reward charts --- README.md | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 5d6b84d..ddbd4af 100644 --- a/README.md +++ b/README.md @@ -7,12 +7,18 @@ The model learns to play very well after 3000 epochs, but not completely flawles 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 after 3000 epochs (~5 minutes on an Intel(R) Core(TM) i7-4770HQ CPU @ 2.20GHz): + ![after training](/demo/flappy-success.gif) -also see: [Before training](/demo/flappy-lose.gif) +Before training: + +![Before training](/demo/flappy-lose.gif) For each frame the bird stays alive, +0.1 score is given to him. For each wall he passes, +10 score is given. +Demonstration of rewards for individuals and the mean reward over time (y axis is logarithmic): +![reward chart](fig-log.jpg) + Try it yourself --------------- You need python3.5 and pip for installing and running the code.