Enum TaskWeightingStrategy 

pub enum TaskWeightingStrategy {
    Fixed,
    DynamicTaskPrioritization,
    GradNorm {
        alpha: f64,
    },
    UncertaintyWeighting,
}

Strategy for weighting multiple tasks.

Variants

Fixed

Fixed weights for each task.

DynamicTaskPrioritization

Dynamic Task Prioritization (DTP) - weights based on task difficulty.

GradNorm

GradNorm - balances gradient magnitudes across tasks.

Fields

alpha: f64

UncertaintyWeighting

Uncertainty weighting - learns task weights from homoscedastic uncertainty.

Trait Implementations

impl Clone for TaskWeightingStrategy

fn clone(&self) -> TaskWeightingStrategy

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TaskWeightingStrategy

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

Formats the value using the given formatter.

impl PartialEq for TaskWeightingStrategy

fn eq(&self, other: &TaskWeightingStrategy) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Copy for TaskWeightingStrategy

impl StructuralPartialEq for TaskWeightingStrategy