search

stober / td

Temporal Difference Learning in Python
12 stars 6 forks source link

OpenAI Gym environment #1

Open MartinThoma opened 7 years ago

MartinThoma commented 7 years ago

You might want to use an OpenAI gym environment (see https://github.com/MartinThoma/banana-gym for an extremely simple example). This would allow others to easily use your algorithm for other environments.

MartinThoma commented 7 years ago

For CartPole, there is already two:

So there is no reason for creating https://github.com/stober/cartpole