Struct A2cStats

Source

pub struct A2cStats {
    pub policy_loss: f64,
    pub value_loss: f64,
    pub entropy: f64,
    pub total_loss: f64,
}

Expand description

Per-update A2C training statistics.

Purpose-built (rather than reusing PPO’s TrainingStats) because A2C has no clip-fraction / KL / explained-variance diagnostics — the loop performs a single un-clipped update. All fields are finite host-side f64s pulled off the autograd tape after the gradient step.

Fields§

§policy_loss: f64

Policy-gradient loss -mean(log_prob * advantage).

§value_loss: f64

Plain-MSE value loss mean((V(s) - returns)^2).

§entropy: f64

Mean per-row policy entropy (the bonus, before negation/scaling).

§total_loss: f64

Total optimized loss policy_loss + value_coef * value_loss + entropy_coef * entropy_loss.

A2cStats

Struct A2cStats Copy item path

Fields§

Trait Implementations§

impl Clone for A2cStats

fn clone(&self) -> A2cStats

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

impl Copy for A2cStats

impl Debug for A2cStats

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

impl Default for A2cStats

fn default() -> A2cStats

Auto Trait Implementations§

impl Freeze for A2cStats

impl RefUnwindSafe for A2cStats

impl Send for A2cStats

impl Sync for A2cStats

impl Unpin for A2cStats

impl UnsafeUnpin for A2cStats

impl UnwindSafe for A2cStats

Blanket Implementations§

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

fn type_id(&self) -> TypeId

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

fn borrow(&self) -> &T

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

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

impl<T> CloneToUninit for Twhere T: Clone,

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

impl<T> From<T> for T

fn from(t: T) -> T

impl<T> Instrument for T

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

fn in_current_span(self) -> Instrumented<Self>

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

fn into(self) -> U

impl<T> IntoEither for T

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

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

impl<T> Pointable for T

const ALIGN: usize

type Init = T

unsafe fn init(init: <T as Pointable>::Init) -> usize

unsafe fn deref<'a>(ptr: usize) -> &'a T

unsafe fn deref_mut<'a>(ptr: usize) -> &'a mut T

unsafe fn drop(ptr: usize)

impl<T> ToOwned for Twhere T: Clone,

type Owned = T

fn to_owned(&self) -> T

fn clone_into(&self, target: &mut T)

impl<T, U> TryFrom<U> for Twhere U: Into<T>,

type Error = Infallible

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

impl<T, U> TryInto<U> for Twhere U: TryFrom<T>,

type Error = <U as TryFrom<T>>::Error

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

impl<V, T> VZip<V> for Twhere V: MultiLane<T>,

fn vzip(self) -> V

impl<T> WithSubscriber for T

fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self>where S: Into<Dispatch>,

fn with_current_subscriber(self) -> WithDispatch<Self>

Struct A2cStats

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

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

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

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

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

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

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

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

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

impl<V, T> VZip<V> for T
where V: MultiLane<T>,

fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self>
where S: Into<Dispatch>,