Skip to content

Ahmar1997/Gridworld-with-Q-learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

b055d25 · Jan 6, 2023

History

9 Commits
Jan 6, 2023
Jan 6, 2023
Jan 6, 2023

Repository files navigation

Gridworld-with-Q-learning

Implentation of the Q learning algorithm in a Gridworld environent

walls image

Ojective

The goal of the game is for the agent to reach the endpoint in least amount of steps as possible

Environment

The environment contains a 10x10 grid containing walls at different locations, a starting point at (1,1) and an end point at (10,10)

Actions

The agent can take four actions: up, down, left and right, If the agent bumps into a wall it will return to its previous location with zero reward

Rewards

+10 reward for reaching the goal
-1 for each step that does not hit a wall
-5 for each step that hits a wall

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages