Skip to content

Repository files navigation

Demo

Left: a Deep Q-Network-based agent trained on a Macbook for several hours plays Snake. Right: cell-wise attributions of the policy network obtained by taking the gradient of the network's output with respect to the inputs.

About

Deep Q-Network based AI for the game Snake

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages