Snake game gym environment with RL agents for solving it.
This was done over a year before it was published here as a public repository and it was of my first endeavors in reinforcement learning. The task was one of the warmups in OpenAI's Requests for Research 2.0.
To install the environment open the terminal and enter the following commands:
git clone https://github.com/AleksaC/snake.git
cd gym-snake
python -m pip install .
Note:
To be able to use the environment you need to import gym_snake
before
making the environment
Unfortunately I didn't have time to try out various types of agents when I was working on this so there's only implementation of vanilla policy gradient algorithm. It was built with tf.keras so you need to have tensorflow installed to be able to run it.
If you want to reach out to me to make an inquiry about this project
or for something else you can contact me through my
personal website or via social media linked there.
If you want to stay up to date with my latest projects you should follow me
on twitter: