Reinforcement_Learning

A repository for studying reinforcement learning.

Cart Pole

As a first step, I taught my agent to master Cart Pole!

Pretty cool huh? More details can be found in the Cart Pole notebook.

Moving on to Mountain Car:

This agent can land on the moon with just one hidden layer of 50 nodes!

Name		Name	Last commit message	Last commit date
Latest commit History 39 Commits
img		img
models		models
recording		recording
.gitignore		.gitignore
README.md		README.md
RL_Acrobot.ipynb		RL_Acrobot.ipynb
RL_BipedalWalker.ipynb		RL_BipedalWalker.ipynb
RL_CartPole.ipynb		RL_CartPole.ipynb
RL_Games.ipynb		RL_Games.ipynb
RL_LunarLander.ipynb		RL_LunarLander.ipynb
RL_MountainCar.ipynb		RL_MountainCar.ipynb
RL_Summary.ipynb		RL_Summary.ipynb