Skip to content

EricSoBo/DeepQLearning

Repository files navigation

DeepQLearning

Using Reinforcement Learning (Deep Q-Learning) to train the agent in several games.

Early stages of training:

rl-video-episode-0

Final stage of training (52min to reach the maximum score 3 times in colab - 186 episodes):

rl-video-episode-0 (1)

The Pytorch model got it in less than 1 minute (218 episodes - not in colab)

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published