Reinforcement Learning Zoo

A central location for my reinforcement learning experiments

Gists

For minimalist, concept-based code:

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)

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

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

Name		Name	Last commit message	Last commit date
Latest commit History 20 Commits
.ipynb_checkpoints		.ipynb_checkpoints
Pong-v0		Pong-v0
models		models
rnn_models		rnn_models
static		static
.DS_Store		.DS_Store
README.md		README.md
cartpole.ipynb		cartpole.ipynb
cartpole.py		cartpole.py
convpong.py		convpong.py
convpong_1frame.py		convpong_1frame.py
dynamic_plotting.py		dynamic_plotting.py
modular_cartpole.ipynb		modular_cartpole.ipynb
modular_pong.py		modular_pong.py
pong modular V2.ipynb		pong modular V2.ipynb
pong modular.ipynb		pong modular.ipynb
pong rnn.ipynb		pong rnn.ipynb
pong.ipynb		pong.ipynb
replay.ipynb		replay.ipynb
rl_pong.py		rl_pong.py
rnnpong.py		rnnpong.py