Skip to content

ml-lab/TorchQLearningExample

 
 

Repository files navigation

TorchQLearning

TorchPlaysCatch

(Not the best player in the world!)

Torch plays catch! Based on Eder Santanas' implementation in keras. Highly recommend reading his informative and easy to follow blog post here.

Agent has to catch the fruit before it falls to the ground. Agent wins if he succeeds to catch the fruit, loses if he fails.

Dependencies

To install torch7 follow the guide here.

Other dependencies can be installed via luarocks:

Optim: numeric optimization package for Torch:

luarocks install optim

visualization

Visualization implemented in itorch. Click here for install instructions.

To run, type into terminal:

itorch notebook

And navigate to the TorchPlaysCatch.pynb. Run the kernel (you must've installed the above dependencies).

Eder Santana, Keras plays catch, (2016), GitHub repository, https://gist.github.com/EderSantana/c7222daa328f0e885093

About

Implementation of a simple example of Q learning in Torch.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 99.1%
  • Lua 0.9%