Struct NatureDqnQNetwork 

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

Nature-DQN-scale Q-network CNN on Burn.

Same conv trunk as NatureDqnBurnPolicy, but with a single q_head whose outputs are interpreted directly as Q(s, a) (no softmax). Includes a record-based copy_params_from for target-net sync, mirroring crate::policy::q_network::QNetworkBurn.

Implementations

impl<B: Backend> NatureDqnQNetwork<B>

pub fn new(n_actions: usize, device: &B::Device) -> Self

Construct a fresh Q-network with unseeded (Burn-default) init.

pub fn with_config( n_actions: usize, config: NatureDqnConfig, device: &B::Device, ) -> Self

Construct a fresh Q-network with the given configuration.

When config.seed is Some, the two FC layers (0 = fc_common, 1 = q_head) are built from deterministically-derived host-side RNG streams. Conv layers are always unseeded.

pub fn forward(&self, obs: Tensor<B, 4>) -> Tensor<B, 2>

Forward pass: compute Q(s, a) for every action a.

• obs shape [batch, 4, 84, 84] (NCHW, pixels in 0.0..=1.0).
• Returns Q-values of shape [batch, n_actions].

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

Replace this network’s parameters with a deep copy of source’s parameters (target-net sync). Returns a new module, mirroring crate::policy::q_network::QNetworkBurn::copy_params_from.

Trait Implementations

impl<B> AutodiffModule<B> for NatureDqnQNetwork<B>

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

type InnerModule = NatureDqnQNetwork<<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 NatureDqnQNetwork<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 NatureDqnQNetwork<B>

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

Formats the value using the given formatter.

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

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

Formats the value using the given formatter.

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

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

type TrainModule = NatureDqnQNetwork<B>

The module with auto-differentiation.

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

type Record = NatureDqnQNetworkRecord<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 NatureDqnQNetwork<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 NatureDqnQNetwork<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.