NN + RL for Flappy Birds
An agent trained to play Flappy Birds using Q learning and Neural Networks. Our project for the Neural Networks course in 2019.
The learning environment used is from PyGame-Learning-Environment.
Results of our best agent ( vertical -> score, horizontal -> number of games played):
Two hidden layers, with leaky relu and tanh as activation functions and Adadelta as optimizer.
-
Notifications
You must be signed in to change notification settings - Fork 0
cotaoctavian/Flappy-Birds
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Flappy Birds using neural network & reinforcement learning.
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published