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

Wrong target value in DDQN implementation #21

Open

xuziye0327 opened this issue Dec 17, 2024 · 0 comments

xuziye0327 commented Dec 17, 2024

Hi!

Current implementation of target value in DDQN should be wrong. It is the target value of DQN actually.

https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/blob/a518f16cfcba84b774fcbfe136a9f439ce94c231/Deep_Reinforcement_Learning_with_Double_Q_learning/ddqn.py#L88C21-L88C94

DQN:

In DDQN, we should use argmax(u) of online network:

    # DDQN
    with torch.no_grad():
        next_q_values = target_q_net(next_state)
        double_q = q_net(next_state).argmax(dim=1)
        next_q_values = next_q_values.gather(1, double_q.unsqueeze(1)).squeeze(1)

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