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

Network 클래스 질문 #129

Open
Yang-Hyun-Jun opened this issue Dec 22, 2021 · 1 comment
Open

Network 클래스 질문 #129

Yang-Hyun-Jun opened this issue Dec 22, 2021 · 1 comment
Labels
question Further information is requested v2

Comments

@Yang-Hyun-Jun
Copy link

Yang-Hyun-Jun commented Dec 22, 2021

  1. shared_network 인자는 None이 아니면 클래스에서 직접 생성하는 DNN, LSTM, CNN을 제외한 다른 형태의 공유 신경망을 받는건가요?

  2. 클래스 함수 get_shared_network에서 net="cnn"인 경우 Input shape이 (num_steps, input_dim, 1)인 것 같은데 맞나요?

@quantylab
Copy link
Owner

  1. shared_network는 가치신경망과 정책신경망을 모두 사용하는 AC, A2C 등에서 두 신경망이 공유하는 앞단 부분을 의미합니다.
  2. input shape는 Conv2D 사용할 경우 (1, num_steps, input_dim), Conv1D 사용할 경우 (num_steps, input_dim)로 정했습니다. input_shape의 마지막은 feature vector size가 되어야해서 input_dim 넣어주시면 됩니다. https://github.com/quantylab/rltrader/blob/v3.0/quantylab/rltrader/networks_keras.py#L60

@quantylab quantylab added v2 question Further information is requested labels Dec 26, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested v2
Projects
None yet
Development

No branches or pull requests

2 participants