Applying Reinforcement Learning To Infinite-Play And Random Environments: Exploring Optimal Performance In Flappy Bird Through Varying Q-Learning Algorithms
Aadarsh Jha
CS 5891: Reinforcement Learning
December 10th, 2021
CS 5891: Reinforcement Learning
December 10th, 2021
Please follow the below instructions to see how both trials of the experiments are run, with respect to Deep Q-Learning and Q-Learning.
-
First,
git clone https://github.com/aadarshjha/flappy.git
or download this repository from the above link. -
Then,
cd flappy/
and follow the below instructions to run the experiments.
- To execute testing and training of the Deep Q-Learning pipeline,
cd
to thedeep-q-learning
directory. - Open the
deep-q-learning.ipynb
, instructions are provided in the notebook itself so as to get you started. - Note that models are provided from the best performing trial, more are available at request. Please email me: aadarsh.jha@vanderbilt.edu
- To execute testing and training of the Deep Q-Learning pipeline,
cd
to theq-learning
directory. - Open the
q-learning.ipynb
, instructions are provided in the notebook itself so as to get you started. - Note that models are provided from the best performing trial, more are available at request. Please email me: aadarsh.jha@vanderbilt.edu
- Due to the number of charts in the paper, some figures may be hard to read.
cd figures/
to find high resolutoin.pdf
files that are the figures.
- As stated in the paper the following repos are drawn inspriation from to execute the Deep Q-Learning and Q-Learning experiments:
- Deep Q-Learning: https://github.com/yenchenlin/DeepLearningFlappyBird
- Q-Learning: https://github.com/yashkotadia/FlapPy-Bird-RL-Q-Learning-Bot
- Enviornment: https://github.com/sourabhv/FlapPyBird