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

[Feature] Store MARL parameters in module #2351

Merged
merged 2 commits into from
Aug 3, 2024
Merged

[Feature] Store MARL parameters in module #2351

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
05075e6
init
vmoens Aug 2, 2024
99f5dcc
amend
vmoens Aug 2, 2024
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
Prev Previous commit
amend
  • Loading branch information
@vmoens
vmoens committed Aug 2, 2024
commit 99f5dccd8f84b9cd67f2cd5d002544abd933dcc3
10 changes: 10 additions & 0 deletions torchrl/modules/models/multiagent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -318,6 +318,11 @@ class MultiAgentMLP(MultiAgentNetBase):
default: 32.
activation_class (Type[nn.Module]): activation class to be used.
default: nn.Tanh.
use_td_params (bool, optional): if ``True``, the parameters can be found in `self.params` which is a
:class:`~tensordict.nn.TensorDictParams` object (which inherits both from `TensorDict` and `nn.Module`).
If ``False``, parameters are contained in `self._empty_net`. All things considered, these two approaches
should be roughly identical but not interchangeable: for instance, a ``state_dict`` created with
``use_td_params=True`` cannot be used when ``use_td_params=False``.
**kwargs: for :class:`torchrl.modules.models.MLP` can be passed to customize the MLPs.

.. note:: to initialize the MARL module parameters with the `torch.nn.init`
Expand Down Expand Up @@ -497,6 +502,11 @@ class MultiAgentConvNet(MultiAgentNetBase):
Defaults to ``2``.
activation_class (Type[nn.Module]): activation class to be used.
Default to :class:`torch.nn.ELU`.
use_td_params (bool, optional): if ``True``, the parameters can be found in `self.params` which is a
:class:`~tensordict.nn.TensorDictParams` object (which inherits both from `TensorDict` and `nn.Module`).
If ``False``, parameters are contained in `self._empty_net`. All things considered, these two approaches
should be roughly identical but not interchangeable: for instance, a ``state_dict`` created with
``use_td_params=True`` cannot be used when ``use_td_params=False``.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Defaults to True missing from docs

**kwargs: for :class:`~torchrl.modules.models.ConvNet` can be passed to customize the ConvNet.


Expand Down
Loading