New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Visualizing gym training #242

Merged

AlexKuhnle merged 2 commits into tensorforce:master from vwxyzjn:Visualizing_gym_training

Nov 23, 2017

Contributor

vwxyzjn commented Nov 22, 2017 •

edited

It might be desirable to visualize the training of agents for two reasons.

A person might get a better understanding of the agent's performance by eyeballing the training process rather than the scalar reward.
It would be visualizing appealing for demo purposes

Thus, I added a simple parameter to enable such feature over gym's environment. One could use

env = OpenAIGym('CartPole-v0', visualize=True)

to visualize the training process.

vwxyzjn added 2 commits

November 22, 2017 16:47


          Add API to visualize the training of gym's environment

e6ee264


          Update quickstart.py to visualize training

fa3dfd3

AlexKuhnle merged commit eef5c7c into tensorforce:master

Member

AlexKuhnle commented Nov 23, 2017

Many thanks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment