Skip to content

Q-Learning and Deep Q-Learning agents learning to play Nim

License

Notifications You must be signed in to change notification settings

frasalvi/DQL_Nim

Repository files navigation

DQL_Nim

In this project, we use Q-Learning and Deep Q-Learning to train artificial agents that can play the famous game of Nim.

Our experiments and findings are summarized in our Report, following the intructions of the project.

This work is part of an assignment for the course "Artificial Neural Networks" at EPFL, and is the joint effort of Francesco Salvi and Bruno Ploumhans.

About

Q-Learning and Deep Q-Learning agents learning to play Nim

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published