In this project I programmed a Q-learning algorithm and used it to play a simple game. The goal was to gain better insight into Q-learning, and see in action such concepts as exploration-vs-exploitation, choice of parameters, limitations of discrete world, etc. It was fun to see AI controlling an agent.
-
Notifications
You must be signed in to change notification settings - Fork 2
In this project I programmed a Q-learning algorithm and used it to play a simple game. The goal was to gain better insight into Q-learning, and see in action such concepts as exploration-vs-exploitation, choice of parameters, limitations of discrete world, etc. It was fun to see AI controlling an agent.
sdthapar/Q-Learning-Hot-Air-balloon-Reinforcement-Learning-
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
In this project I programmed a Q-learning algorithm and used it to play a simple game. The goal was to gain better insight into Q-learning, and see in action such concepts as exploration-vs-exploitation, choice of parameters, limitations of discrete world, etc. It was fun to see AI controlling an agent.
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published