Skip to content
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.

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

A question about DQN_With_Fixed_Q_Targets. #82

Open
LLYYKK opened this issue May 25, 2022 · 0 comments
Open

A question about DQN_With_Fixed_Q_Targets. #82

LLYYKK opened this issue May 25, 2022 · 0 comments

Comments

@LLYYKK
Copy link

LLYYKK commented May 25, 2022

According to the paper, the target network should be updated several steps after local network update, but your code seem to be not like this. In your code, the local network updates are followed by soft updates to the target network. I think there needs to be some time between local network updates and target network updates.

def learn(self, experiences=None):
"""Runs a learning iteration for the Q network"""
super(DQN_With_Fixed_Q_Targets, self).learn(experiences=experiences)
self.soft_update_of_target_network(self.q_network_local, self.q_network_target, self.hyperparameters["tau"])

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

No branches or pull requests

1 participant