Struct SacActor 

pub struct SacActor<B: Backend> { /* private fields */ }

Stochastic, tanh-squashed Gaussian actor for SAC continuous control.

Layout:

obs → fc1 →act→ fc2 →act→ (fc3 →act→)? ┬─ mean_head    (μ)
                                       └─ log_std_head (log σ, clamped)

Both heads share the trunk activations. Use sample for a reparameterized stochastic action with its (squash-corrected) log-probability, and mean_action for the deterministic evaluation action tanh(μ).

Implementations

impl<B: Backend> SacActor<B>

pub fn with_config( obs_dim: usize, action_dim: usize, config: SacActorConfig, device: &B::Device, ) -> Self

Build a fresh actor on device with the given configuration.

obs_dim is the observation width; action_dim is the number of continuous action dimensions (each squashed into (-1, 1)).

pub fn forward(&self, obs: Tensor<B, 2>) -> (Tensor<B, 2>, Tensor<B, 2>)

Forward pass producing the Gaussian parameters (mean, log_std), each shape [batch, action_dim].

log_std is clamped to [LOG_STD_MIN, LOG_STD_MAX] before being returned.

pub fn mean_action(&self, obs: Tensor<B, 2>) -> Tensor<B, 2>

Deterministic evaluation action tanh(μ), shape [batch, action_dim], lying in the open box (-1, 1).

Used at evaluation time when the stochastic exploration of sample is undesirable.

pub fn sample( &self, obs: Tensor<B, 2>, rng: &mut StdRng, ) -> (Tensor<B, 2>, Tensor<B, 1>)

Draw one reparameterized, tanh-squashed action per row and return (action, log_prob).

• action is shape [batch, action_dim], every element in the open box (-1, 1).
• log_prob is shape [batch] — the joint log-density over all action dimensions, with the tanh-squash change-of-variables correction applied.

The Gaussian noise eps is drawn on the host from rng (via the Box–Muller transform, matching crate::policy::seeded_init) and injected as a constant tensor, so gradients still flow through mean and std (the reparameterization trick) while the sample stays bit-exactly reproducible for a given seed — mirroring crate::policy::mlp::MlpBurnPolicy::get_action_host_seeded.

pub fn fc1(&self) -> &Linear<B>

Borrow the first shared-trunk linear layer.

pub fn fc2(&self) -> &Linear<B>

Borrow the second shared-trunk linear layer.

pub fn mean_head(&self) -> &Linear<B>

Borrow the mean head.

pub fn log_std_head(&self) -> &Linear<B>

Borrow the log-std head.

Trait Implementations

impl<B> AutodiffModule<B> for SacActor<B>

where B: AutodiffBackend + Backend, <B as AutodiffBackend>::InnerBackend: Backend,

type InnerModule = SacActor<<B as AutodiffBackend>::InnerBackend>

Inner module without auto-differentiation.

fn valid(&self) -> Self::InnerModule

Returns the same module, but on the inner backend without auto-differentiation.

fn from_inner(module: Self::InnerModule) -> Self

Wraps an inner module back into an auto-diff module.

impl<B: Backend> Clone for SacActor<B>

fn clone(&self) -> Self

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl<B: Debug + Backend> Debug for SacActor<B>

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<B: Backend> Display for SacActor<B>

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<B> HasAutodiffModule<B> for SacActor<B::InnerBackend>

where B: AutodiffBackend + Backend, <B as AutodiffBackend>::InnerBackend: Backend,

type TrainModule = SacActor<B>

The module with auto-differentiation.

impl<B: Backend> Module<B> for SacActor<B>

type Record = SacActorRecord<B>

Type to save and load the module.

fn load_record(self, record: Self::Record) -> Self

Load the module state from a record.

fn into_record(self) -> Self::Record

Convert the module into a record containing the state.

fn num_params(&self) -> usize

Get the number of parameters the module has, including all of its sub-modules.

fn visit<Visitor: ModuleVisitor<B>>(&self, visitor: &mut Visitor)

Visit each tensor parameter in the module with a visitor.

fn map<Mapper: ModuleMapper<B>>(self, mapper: &mut Mapper) -> Self

Map each tensor parameter in the module with a mapper.

fn collect_devices(&self, devices: Devices<B>) -> Devices<B>

Return all the devices found in the underneath module tree added to the given vector without duplicates.

fn to_device(self, device: &B::Device) -> Self

Move the module and all of its sub-modules to the given device.

fn fork(self, device: &B::Device) -> Self

Fork the module and all of its sub-modules to the given device.

fn devices(&self) -> Vec<<B as BackendTypes>::Device>

Return all the devices found in the underneath module tree without duplicates.

fn no_grad(self) -> Self

Each tensor in the module tree will not require grad.

fn train<AB>(self) -> Self::TrainModule

where AB: AutodiffBackend<InnerBackend = B>, Self: HasAutodiffModule<AB>,

Move the module and all of its sub-modules to the autodiff backend.

fn save_file<FR, PB>( self, file_path: PB, recorder: &FR, ) -> Result<(), RecorderError>

where FR: FileRecorder<B>, PB: Into<PathBuf>,

Save the module to a file using the provided file recorder.

fn load_file<FR, PB>( self, file_path: PB, recorder: &FR, device: &<B as BackendTypes>::Device, ) -> Result<Self, RecorderError>

where FR: FileRecorder<B>, PB: Into<PathBuf>,

Load the module from a file using the provided file recorder.

fn quantize_weights(self, quantizer: &mut Quantizer) -> Self

Quantize the weights of the module.

impl<B: Backend> ModuleDisplay for SacActor<B>

fn format(&self, passed_settings: DisplaySettings) -> String

Formats the module with provided display settings.

fn custom_settings(&self) -> Option<DisplaySettings>

Custom display settings for the module.

fn custom_content(&self, _content: Content) -> Option<Content>

Custom attributes for the module.

impl<B: Backend> ModuleDisplayDefault for SacActor<B>

fn content(&self, content: Content) -> Option<Content>

Attributes of the module used for display purposes.

fn num_params(&self) -> usize

Gets the number of the parameters of the module.