Struct ContinuousQNetwork 

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

Continuous-action Q-critic on Burn: Q(s, a) -> scalar.

Implementations

impl<B: Backend> ContinuousQNetwork<B>

pub fn new( obs_dim: usize, action_dim: usize, hidden_dim: usize, device: &B::Device, ) -> Self

Build a fresh critic with the default config (2-layer ReLU, orthogonal init) and the given hidden width.

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

Build a fresh critic with the given configuration.

The trunk input width is obs_dim + action_dim (the concatenated (state, action) feature vector). When config.seed is Some, every layer is drawn from a per-layer-derived StdRng stream so the construction is bit-exact across runs and machines.

pub fn forward(&self, obs: Tensor<B, 2>, action: Tensor<B, 2>) -> Tensor<B, 1>

Forward pass: compute Q(s, a) for a batch of (state, action) pairs.

• obs shape [batch, obs_dim].
• action shape [batch, action_dim].
• Returns Q-values of shape [batch] (the trailing singleton head dimension is squeezed).

The observation and action are concatenated along the feature axis before the trunk, so gradients flow into both inputs — SAC’s actor loss differentiates Q(s, a) with respect to the action.

pub fn copy_params_from( self, source: &ContinuousQNetwork<B>, ) -> ContinuousQNetwork<B>

Replace this critic’s parameters with a deep copy of source’s (hard target sync, theta_target <- theta_online).

Returns a new module with the same architecture but source’s records. Burn’s optimizer ownership model (step consumes the module by value) means we return Self rather than mutating &mut self; the trainer holds each target critic as a field and swaps it through this call when initializing the targets.

pub fn soft_update_from(&mut self, online: &ContinuousQNetwork<B>, tau: f64)

Polyak (soft) target update: theta_target <- tau * theta_online + (1 - tau) * theta_target.

Applied to every parameter tensor (every trunk layer’s weight and bias, plus the Q-head’s). tau = 1.0 reduces exactly to a hard copy (copy_params_from); a tau in (0, 1) nudges the target toward the online network — the always-soft update SAC performs every gradient step.

Mutates self in place. self (the target) and online must share the same architecture (depth, widths); the trainer constructs the targets as clones of the online critics, so this holds by construction.

Trait Implementations

impl<B> AutodiffModule<B> for ContinuousQNetwork<B>

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

type InnerModule = ContinuousQNetwork<<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 ContinuousQNetwork<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 ContinuousQNetwork<B>

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

Formats the value using the given formatter.

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

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

Formats the value using the given formatter.

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

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

type TrainModule = ContinuousQNetwork<B>

The module with auto-differentiation.

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

type Record = ContinuousQNetworkRecord<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 ContinuousQNetwork<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 ContinuousQNetwork<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.