Inspiration
Interested in exploring interactions between spaceships and planet gravity and how this can be automated.
What it does
We have created an environment for training and testing different reinforcement learning models to learn what models are best at space navigation.
How we built it
We used openai gym to create a new module. In addition we also used pyglet to render the current state of the environment.
Challenges we ran into
There were a lot of them. Come by and we will tell you.
Accomplishments that we're proud of
It works.
What I learned
Rendering is challenging and trying to approximated gravity doesn't always work well.
Log in or sign up for Devpost to join the conversation.