Skip to content

Average the loss? #5

New issue
New issue
Open
Open
Average the loss?#5
@heli-sudoo

Description

@heli-sudoo
heli-sudoo
opened on Jan 4, 2022

berkeley-deep-RL-pytorch-solutions/hw2/cs285/policies/MLP_policy.py

Line 115 in 47da611

loss = torch.sum((-logprob_pi * torch.Tensor(adv_n).to(self.device)))

Shall the loss be averaged by N? I apologize if I am wrong. Do not have much experience with RL. Thanks.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions