Struct LinearGaussianPolicy 

pub struct LinearGaussianPolicy<T: Float + Debug + Send + Sync + 'static> { /* private fields */ }

Diagonal Gaussian policy a ~ N(W φ(s), diag(σ²)) with σ = exp(log_std).

Both the mean weights and the (state-independent) log standard deviations are trainable parameters, exposed as "weights" and "log_std". All gradients are closed form:

∇_W      log π(a|s) = ((a − μ)/σ²) φ(s)ᵀ
∇_logσ_j log π(a|s) = (a_j − μ_j)²/σ_j² − 1
∇_logσ_j H[π]       = 1                      ∇_W H[π] = 0
∇_W  Σ_ij w_ij μ_j(s_i) = Σ_i w_i φ(s_i)ᵀ    (deterministic-policy-gradient hook)

Implementations

impl<T: Float + Debug + Send + Sync + 'static> LinearGaussianPolicy<T>

pub fn new(action_dim: usize, n_features: usize, init_std: T) -> Result<Self>

Create a zero-mean policy with the given initial standard deviation.

pub fn action_dim(&self) -> usize

Action dimension.

pub fn n_features(&self) -> usize

Observation/feature dimension.

pub fn weights(&self) -> &Array2<T>

Current mean weights.

pub fn std(&self) -> Array1<T>

Current standard deviations (clamped away from zero).

pub fn mean_actions(&self, observations: &Array2<T>) -> Result<Array2<T>>

Deterministic mean action μ(s) = W φ(s), shape (n, action_dim).

pub fn sample_actions_with( &self, observations: &Array2<T>, standard_normal: impl FnMut() -> f64, ) -> Result<(Array2<T>, Array1<T>)>

Sample actions with a caller-supplied standard-normal source.

Returns the sampled actions and their log-probabilities.

Trait Implementations

impl<T: Clone + Float + Debug + Send + Sync + 'static> Clone for LinearGaussianPolicy<T>

fn clone(&self) -> LinearGaussianPolicy<T>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<T: Debug + Float + Debug + Send + Sync + 'static> Debug for LinearGaussianPolicy<T>

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

Formats the value using the given formatter.

impl<T: Float + Debug + Send + Sync + 'static> PolicyNetwork<T> for LinearGaussianPolicy<T>

fn evaluate_actions( &self, observations: &Array2<T>, actions: &Array2<T>, ) -> Result<PolicyEvaluation<T>>

Evaluate actions for given observations

fn get_action_distribution( &self, observations: &Array2<T>, ) -> Result<ActionDistribution<T>>

Get action distribution for given observations

fn update_parameters( &mut self, deltas: &HashMap<String, Array1<T>>, ) -> Result<()>

Add a parameter delta to the policy parameters (see the trait docs).

fn get_parameters(&self) -> HashMap<String, Array1<T>>

Get current policy parameters

fn log_prob_gradient( &self, observations: &Array2<T>, actions: &Array2<T>, coefficients: &Array1<T>, ) -> Result<HashMap<String, Array1<T>>>

Gradient of a coefficient-weighted sum of log-probabilities: ∂/∂θ Σᵢ cᵢ · log π(aᵢ | sᵢ).

fn entropy_gradient( &self, observations: &Array2<T>, ) -> Result<HashMap<String, Array1<T>>>

Gradient of the batch-mean entropy ∂/∂θ (1/N) Σᵢ H[π(·|sᵢ)].

fn mean_action_gradient( &self, observations: &Array2<T>, weights: &Array2<T>, ) -> Result<HashMap<String, Array1<T>>>

Gradient of a weighted sum of the distribution mean: ∂/∂θ Σᵢ Σⱼ w[i,j] · μⱼ(sᵢ).

fn kronecker_factors( &self, observations: &Array2<T>, actions: &Array2<T>, ) -> Result<Vec<KroneckerBlock<T>>>

Per-sample Kronecker factors of the Fisher information matrix.

fn score_matrix( &self, observations: &Array2<T>, actions: &Array2<T>, ) -> Result<Array2<T>>

Per-sample score vectors g_i = ∇_θ log π(aᵢ|sᵢ), one per row, flattened with flatten_named’s canonical layout.