This is a demo of how Q-Learning can be used to find an optimal policy for an agent in a grid to stay along
the main diagonal of a square matrix in the left-ish side of the grid. Training is initiated with an arrow key.
When training is done, the d
key concludes training and follows the optimal policy and the r
key
resets the state to the start state.
sebLopezCot/Q-Learning-Gridworld
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
A demo of Q-Learning in a javascript canvas grid.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published