Skip to main content

PpoConfig

ember_rl::algorithms::ppo

Struct PpoConfig 

Source 
pub struct PpoConfig {
    pub n_steps: usize,
    pub n_envs: usize,
    pub n_epochs: usize,
    pub batch_size: usize,
    pub learning_rate: f64,
    pub clip_epsilon: f64,
    pub value_loss_coef: f64,
    pub entropy_coef: f64,
    pub gamma: f64,
    pub gae_lambda: f64,
    pub hidden_sizes: Vec<usize>,
    pub max_grad_norm: f64,
}
Expand description

Hyperparameters for the PPO algorithm.

Fields§

§n_steps: usize

Steps collected per environment before each update. Total rollout size = n_steps * n_envs.

§n_envs: usize

Number of parallel environments feeding this agent. Must match the number of envs in your BevyGymPlugin / training loop.

§n_epochs: usize

Number of gradient epochs over each rollout. Typical: 4-10.

§batch_size: usize

Minibatch size for each gradient step. Must divide n_steps * n_envs evenly.

§learning_rate: f64§clip_epsilon: f64

Clipping range for the probability ratio. Typical: 0.1-0.3.

§value_loss_coef: f64

Weight on the value function loss. Typical: 0.5.

§entropy_coef: f64

Weight on the entropy bonus (encourages exploration). Typical: 0.01.

§gamma: f64

Discount factor.

§gae_lambda: f64

GAE smoothing parameter. 1.0 = full Monte Carlo, 0.0 = TD(0).

§hidden_sizes: Vec<usize>

Hidden layer sizes for the shared trunk.

§max_grad_norm: f64

Clip gradient norm to this value. Set to 0.0 to disable.

Implementations§

Source§

impl PpoConfig

Source

pub fn rollout_size(&self) -> usize

Total number of transitions collected before each update.

Trait Implementations§

Source§

impl Clone for PpoConfig

Source§

fn clone(&self) -> PpoConfig

Returns a duplicate of the value. Read more
1.0.0 · Source§

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

Performs copy-assignment from source. Read more
Source§

impl Debug for PpoConfig

Source§

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

Formats the value using the given formatter. Read more
Source§

impl Default for PpoConfig

Source§

fn default() -> Self

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

impl<'de> Deserialize<'de> for PpoConfig

Source§

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>
where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer. Read more
Source§

impl Serialize for PpoConfig

Source§

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

Serialize this value into the given Serde serializer. Read more

Auto Trait Implementations§

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<U> 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> IntoComptime for T

Source§

fn comptime(self) -> Self

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§

impl<T> Pointable for T

Source§

const ALIGN: usize

The alignment of pointer.
Source§

type Init = T

The type for initializers.
Source§

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

Initializes a with the given initializer. Read more
Source§

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

Dereferences the given pointer. Read more
Source§

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

Mutably dereferences the given pointer. Read more
Source§

unsafe fn drop(ptr: usize)

Drops the object pointed to by the given pointer. Read more
Source§

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

Source§

type Owned = T

The resulting type after obtaining ownership.
Source§

fn to_owned(&self) -> T

Creates owned data from borrowed data, usually by cloning. Read more
Source§

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

Uses borrowed data to replace owned data, usually by cloning. Read more
Source§

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

Source§

type Error = Infallible

The type returned in the event of a conversion error.
Source§

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

Performs the conversion.
Source§

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

Source§

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

The type returned in the event of a conversion error.
Source§

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

Performs the conversion.
Source§

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

Source§

fn vzip(self) -> V

Source§

impl<T> WithSubscriber for T

Source§

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

Attaches the provided Subscriber to this type, returning a WithDispatch wrapper. Read more
Source§

fn with_current_subscriber(self) -> WithDispatch<Self>

Attaches the current default Subscriber to this type, returning a WithDispatch wrapper. Read more
Source§

impl<T> DeserializeOwned for T
where T: for<'de> Deserialize<'de>,