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.

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

[RLlib] Added dtype to torch deterministic action #29648

Merged
merged 12 commits into from
Oct 25, 2022
Merged

[RLlib] Added dtype to torch deterministic action #29648

Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
da8f916
created action_dist_v2 for RLModule examples
kouroshHakha Oct 24, 2022
d366847
Merge branch 'master' into action-dist-v2
kouroshHakha Oct 24, 2022
f96534c
torch.pi to math.pi
kouroshHakha Oct 24, 2022
4bcad07
added missing docstrings and some nit renames
kouroshHakha Oct 24, 2022
486f3d2
lint
kouroshHakha Oct 24, 2022
0a50805
updated test
kouroshHakha Oct 24, 2022
185257e
doscsrig
kouroshHakha Oct 24, 2022
7d12b65
docstring
kouroshHakha Oct 24, 2022
8e86cb2
updated pi
kouroshHakha Oct 24, 2022
3e2933e
lint
kouroshHakha Oct 24, 2022
a0fbc40
Merge branch 'master' into action-dist-v2
kouroshHakha Oct 25, 2022
6f16139
fixed minor thing for torch dist
kouroshHakha Oct 25, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 5 additions & 2 deletions rllib/models/torch/torch_distributions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -219,8 +219,11 @@ def sample(

if sample_shape is None:
sample_shape = torch.Size()
loc_shape = self.loc.shape
return torch.ones(sample_shape + loc_shape, device=self.loc.device) * self.loc

device = self.loc.device
dtype = self.loc.dtype
shape = sample_shape + self.loc.shape
return torch.ones(shape, device=device, dtype=dtype) * self.loc

def rsample(
self,
Expand Down