thrust_rl::train::ppo::stats

Struct TrainingStats

pub struct TrainingStats {
    pub policy_loss: f64,
    pub value_loss: f64,
    pub entropy: f64,
    pub total_loss: f64,
    pub aux_loss: f64,
    pub clip_fraction: f64,
    pub approx_kl: f64,
    pub explained_var: f64,
    pub num_updates: usize,
}

Expand description

Training statistics for a PPO update

Tracks various metrics from a single training step including losses, KL divergence, and other diagnostic information.

Fields§

§policy_loss: f64

Policy loss

§value_loss: f64

Value function loss

§entropy: f64

Entropy bonus

§total_loss: f64

Total loss (weighted sum of policy, value, entropy, and aux losses)

§aux_loss: f64

Auxiliary loss (caller-supplied — e.g. representation regularizer)

§clip_fraction: f64

Fraction of clipped policy updates

§approx_kl: f64

Approximate KL divergence between old and new policies

§explained_var: f64

Explained variance of value function predictions

§num_updates: usize

Number of gradient updates performed

Implementations§

Source §

impl TrainingStats

Source

pub fn zeros() -> Self

Create zero-initialized statistics

Source

pub fn new( policy_loss: f64, value_loss: f64, entropy: f64, total_loss: f64, clip_fraction: f64, approx_kl: f64, explained_var: f64, ) -> Self

Create statistics from scalar values.

aux_loss defaults to 0.0; set with Self::with_aux_loss when an auxiliary loss term is present.

Source

pub fn with_aux_loss(self, aux_loss: f64) -> Self

Builder-style setter for the auxiliary loss field.

Source

pub fn add(&mut self, other: &TrainingStats)

Add another statistics instance to this one

Source

pub fn average(&self) -> Self

Compute average statistics across multiple updates

Trait Implementations§

Source §

impl AddAssign<&TrainingStats> for TrainingStats

Source §

fn add_assign(&mut self, other: &TrainingStats)

Performs the += operation. Read more

Source §

impl Clone for TrainingStats

Source §

fn clone(&self) -> TrainingStats

Returns a duplicate of the value. Read more

1.0.0 (const: unstable) · Source§

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

Performs copy-assignment from source. Read more

Source §

impl Debug for TrainingStats

Source §

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

Formats the value using the given formatter. Read more

Source §

impl Default for TrainingStats

Source §

fn default() -> TrainingStats

Returns the “default value” for a type. Read more

Auto Trait Implementations§

§

impl UnwindSafe for TrainingStats

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> Instrument for T

Source §

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided Span, returning an Instrumented wrapper. Read more

Source §

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more

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 §