Enum OptimizerConfig 

pub enum OptimizerConfig {
    AdamW {
        lr: f64,
        beta1: f64,
        beta2: f64,
        eps: f64,
        weight_decay: f64,
    },
    Adam {
        lr: f64,
    },
}

Configuration of optimizer for training neural networks in an RL agent.

Variants

AdamW

AdamW optimizer.

Fields

lr: f64

beta1: f64

beta2: f64

eps: f64

weight_decay: f64

Adam

Adam optimizer.

Fields

lr: f64

Learning rate.

Implementations

impl OptimizerConfig

pub fn build(&self, vars: Vec<Var>) -> Result<Optimizer>

Constructs AdamW optimizer.

pub fn learning_rate(self, lr: f64) -> Self

Override learning rate.

Trait Implementations

impl Clone for OptimizerConfig

fn clone(&self) -> OptimizerConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for OptimizerConfig

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

Formats the value using the given formatter.

impl Default for OptimizerConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for OptimizerConfig

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for OptimizerConfig

fn eq(&self, other: &OptimizerConfig) -> 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 Serialize for OptimizerConfig

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for OptimizerConfig