Skip to content
This repository was archived by the owner on May 21, 2024. It is now read-only.

Conversation

simonyilunw
Copy link
Contributor

No description provided.

else:
action = self.qtable[state].argsort()[-1]

self.train_iteration += 1
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you move the training code from nextAction() to a new method, like updateModel()? During testing, you want to call nextAction() to only get actions without updating the Q values.

@simonyilunw
Copy link
Contributor Author

Done!

@yukezhu yukezhu merged commit d5e5f32 into yukezhu:master Jun 23, 2016
@yukezhu
Copy link
Owner

yukezhu commented Jun 23, 2016

Merged. Thanks!

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants