Skip to content

A central location for my reinforcement learning experiments

Notifications You must be signed in to change notification settings

greydanus/rlzoo

Repository files navigation

Reinforcement Learning Zoo

A central location for my reinforcement learning experiments

Gists

For minimalist, concept-based code:

Notebooks

There are several notebooks here. Some of them are under active development.

First I solved Cartpole as a toy problem (I know that pg is overkill)

Cartpole gif

Then I used the same algorithm to solve something trickier - Atari Pong!

Pong gif

Code for both of these was derived in part from karpathy's excellent deep rl post.

Dependencies

  • Mostly Python 2.7. You will need:
  • Numpy
  • Matplotlib
  • TensorFlow
  • OpenAI Gym