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

[Docs] Use more appropriate ActorValueOperator in PPOLoss documentation #2350

Merged
merged 1 commit into from
Aug 2, 2024
Merged

[Docs] Use more appropriate ActorValueOperator in PPOLoss documentation #2350

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
[Docs] Use more appropriate ActorValueOperator in PPOLoss documentation
  • Loading branch information
@GaetanLepage
GaetanLepage committed Aug 2, 2024
commit d9e63a97eb9860282368528305481db90262d099
14 changes: 7 additions & 7 deletions torchrl/objectives/ppo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -141,7 +141,7 @@ class PPOLoss(LossModule):
>>> actor_head = SomeActor(in_keys=["hidden"])
>>> value_head = SomeValue(in_keys=["hidden"])
>>> # first option, with 2 calls on the common module
>>> model = ActorCriticOperator(common, actor_head, value_head)
>>> model = ActorValueOperator(common, actor_head, value_head)
>>> loss_module = PPOLoss(model.get_policy_operator(), model.get_value_operator())
>>> # second option, with a single call to the common module
>>> loss_module = PPOLoss(ProbabilisticTensorDictSequential(model, actor_head), value_head)
Expand Down Expand Up @@ -718,10 +718,10 @@ class ClipPPOLoss(PPOLoss):
>>> actor_head = SomeActor(in_keys=["hidden"])
>>> value_head = SomeValue(in_keys=["hidden"])
>>> # first option, with 2 calls on the common module
>>> model = ActorCriticOperator(common, actor_head, value_head)
>>> loss_module = PPOLoss(model.get_policy_operator(), model.get_value_operator())
>>> model = ActorValueOperator(common, actor_head, value_head)
>>> loss_module = ClipPPOLoss(model.get_policy_operator(), model.get_value_operator())
>>> # second option, with a single call to the common module
>>> loss_module = PPOLoss(ProbabilisticTensorDictSequential(model, actor_head), value_head)
>>> loss_module = ClipPPOLoss(ProbabilisticTensorDictSequential(model, actor_head), value_head)

This will work regardless of whether separate_losses is activated or not.

Expand Down Expand Up @@ -955,10 +955,10 @@ class KLPENPPOLoss(PPOLoss):
>>> actor_head = SomeActor(in_keys=["hidden"])
>>> value_head = SomeValue(in_keys=["hidden"])
>>> # first option, with 2 calls on the common module
>>> model = ActorCriticOperator(common, actor_head, value_head)
>>> loss_module = PPOLoss(model.get_policy_operator(), model.get_value_operator())
>>> model = ActorValueOperator(common, actor_head, value_head)
>>> loss_module = KLPENPPOLoss(model.get_policy_operator(), model.get_value_operator())
>>> # second option, with a single call to the common module
>>> loss_module = PPOLoss(ProbabilisticTensorDictSequential(model, actor_head), value_head)
>>> loss_module = KLPENPPOLoss(ProbabilisticTensorDictSequential(model, actor_head), value_head)

This will work regardless of whether separate_losses is activated or not.

Expand Down
Loading