Skip to content

TorsteinOtterlei/peg-solitaire-reinforcement-learning

Repository files navigation

Peg-solitaire-reinforcement-learning

Implementation of peg solitare and the Actor-Critic algorithm to solve the game as shown below. The game board can be a diamond or a triangle of arbitrary size, specified in the parameters.json. Requirements are matplotlib and networkx, simply run main.py

alt text

After 600 episodes (training sessions) the algorithm solves the game flawlessly:

alt text

The number of pegs on the board converges to 1 (win):

alt text

Meme-version for faster speeds:

alt text

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages