Struct AdvancedAdvancedPolicyGradientOptimizer 

pub struct AdvancedAdvancedPolicyGradientOptimizer { /* private fields */ }

Advanced Policy Gradient Optimizer with Meta-Learning

Implementations

impl AdvancedAdvancedPolicyGradientOptimizer

pub fn new( config: RLOptimizationConfig, state_size: usize, actionsize: usize, ) -> Self

Create new advanced policy gradient optimizer

Trait Implementations

impl Clone for AdvancedAdvancedPolicyGradientOptimizer

fn clone(&self) -> AdvancedAdvancedPolicyGradientOptimizer

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AdvancedAdvancedPolicyGradientOptimizer

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

Formats the value using the given formatter.

impl RLOptimizer for AdvancedAdvancedPolicyGradientOptimizer

fn config(&self) -> &RLOptimizationConfig

Configuration

fn select_action(&mut self, state: &OptimizationState) -> OptimizationAction

Select action given current state

fn update(&mut self, experience: &Experience) -> Result<(), OptimizeError>

Update policy/value function based on experience

fn run_episode<F>( &mut self, objective: &F, initial_params: &ArrayView1<'_, f64>, ) -> OptimizeResult<OptimizeResults<f64>>

where F: Fn(&ArrayView1<'_, f64>) -> f64,

Run optimization episode

fn train<F>( &mut self, objective: &F, initial_params: &ArrayView1<'_, f64>, ) -> OptimizeResult<OptimizeResults<f64>>

where F: Fn(&ArrayView1<'_, f64>) -> f64,

Train the RL optimizer

fn reset(&mut self)

Reset optimizer state