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

depth #68

Open
ndrwmlnk opened this issue Mar 7, 2019 · 2 comments
Open

depth #68

ndrwmlnk opened this issue Mar 7, 2019 · 2 comments
Assignees

Comments

@ndrwmlnk
Copy link

ndrwmlnk commented Mar 7, 2019

is there a way to get a depth view for training?
e.g. def render(self, mode='depth')

@kwea123
Copy link

kwea123 commented Mar 7, 2019

It will be too easy if this is provided... that being said, it is easy to train a depth prediction model by yourself.

@awjuliani
Copy link
Contributor

HI @ndrwmlnk

We plan to provide this as an option in the open source release of Obstacle Tower. For now though we want to restrict the observation space for the duration of the challenge we are running.

@awjuliani awjuliani self-assigned this Mar 7, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

3 participants