scirs2_optimize::reinforcement_learning::policy_gradient

Struct MetaPolicyNetwork

pub struct MetaPolicyNetwork {
    pub policy_weights: Array3<f64>,
    pub meta_weights: Array3<f64>,
    pub policy_bias: Array2<f64>,
    pub meta_bias: Array2<f64>,
    pub layer_sizes: Vec<usize>,
    pub adaptive_learning_rates: Array2<f64>,
    pub meta_gradient_accumulator: Array3<f64>,
    pub second_order_info: Array3<f64>,
    pub curriculum_difficulty: f64,
    pub problem_embeddings: HashMap<String, Array1<f64>>,
}

Expand description

Advanced Neural Network with Meta-Learning Capabilities

Fields§

§policy_weights: Array3<f64>

Primary policy weights

§meta_weights: Array3<f64>

Meta-policy weights for learning rate adaptation

§policy_bias: Array2<f64>

Bias terms

§meta_bias: Array2<f64>§layer_sizes: Vec<usize>

Network architecture

§adaptive_learning_rates: Array2<f64>

Adaptive learning rates per parameter

§meta_gradient_accumulator: Array3<f64>

Meta-gradient accumulator

§second_order_info: Array3<f64>

Higher-order derivative tracking

§curriculum_difficulty: f64

Curriculum learning difficulty

§problem_embeddings: HashMap<String, Array1<f64>>

Problem class embeddings

Implementations§

Source §

impl MetaPolicyNetwork

Source

pub fn new( _input_size: usize, output_size: usize, hidden_sizes: Vec<usize>, ) -> Self

Create new meta-policy network with hierarchical structure

Source

pub fn meta_forward( &mut self, state_features: &ArrayView1<'_, f64>, problem_class: &str, meta_context: &Array1<f64>, ) -> (Array1<f64>, Array1<f64>)

Forward pass with meta-learning augmentation

Source

pub fn meta_update( &mut self, meta_gradients: &MetaGradients, base_learning_rate: f64, meta_learning_rate: f64, )

Update network using meta-gradients

Trait Implementations§

Source §

impl Clone for MetaPolicyNetwork

Source §

fn clone(&self) -> MetaPolicyNetwork

Returns a duplicate of the value. Read more

1.0.0 · Source§

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

Performs copy-assignment from source. Read more

Source §

impl Debug for MetaPolicyNetwork

Source §

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

Formats the value using the given formatter. Read more

Auto Trait Implementations§

§

impl UnwindSafe for MetaPolicyNetwork

Blanket Implementations§

Source §

impl<T> Any for T
where T: 'static + ?Sized,

Source §

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more

Source §

impl<T> Borrow<T> for T
where T: ?Sized,

Source §

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more

Source §

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source §

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more

Source §

impl<T> CloneToUninit for T
where T: Clone,

Source §

unsafe fn clone_to_uninit(&self, dest: *mut u8)

🔬This is a nightly-only experimental API. (clone_to_uninit)

Performs copy-assignment from self to dest. Read more

Source §

impl<T> From<T> for T

Source §

fn from(t: T) -> T

Returns the argument unchanged.

Source §

impl<T, U> Into for T
where U: From<T>,

Source §

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Source §

impl<T> IntoEither for T

Source §

fn into_either(self, into_left: bool) -> Either<Self, Self>

Converts self into a Left variant of Either<Self, Self> if into_left is true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more

Source §

fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
where F: FnOnce(&Self) -> bool,

Converts self into a Left variant of Either<Self, Self> if into_left(&self) returns true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more

Source §