pub struct RLComponents<RLC: RLComponentsTypes> {
pub label: Option<String>,
pub num_steps: usize,
pub checkpoint: Option<usize>,
pub checkpointer: Option<RLCheckpointer<RLC>>,
pub grad_accumulation: Option<usize>,
pub interrupter: Interrupter,
pub event_processor: RLEventProcessorType<RLC>,
pub event_store: Arc<EventStoreClient>,
pub summary: Option<LearnerSummaryConfig>,
pub inference_device: Device,
}Available on crate feature
rl only.Expand description
Struct to minimise parameters passed to RLStrategy::train.
Fields§
§label: Option<String>An optional label for this training.
num_steps: usizeThe total number of environment steps.
checkpoint: Option<usize>The step number from which to continue the training.
checkpointer: Option<RLCheckpointer<RLC>>A checkpointer used to load and save learning checkpoints.
grad_accumulation: Option<usize>Enables gradients accumulation.
interrupter: InterrupterAn Interupter that allows aborting the training/evaluation process early.
event_processor: RLEventProcessorType<RLC>An EventProcessor that processes events happening during training and evaluation.
event_store: Arc<EventStoreClient>A reference to an EventStoreClient.
summary: Option<LearnerSummaryConfig>Config for creating a summary of the learning
inference_device: DeviceDevice used for running inference during environmment sampling or validation.
Auto Trait Implementations§
impl<RLC> !RefUnwindSafe for RLComponents<RLC>
impl<RLC> !Sync for RLComponents<RLC>
impl<RLC> !Unpin for RLComponents<RLC>
impl<RLC> !UnsafeUnpin for RLComponents<RLC>
impl<RLC> !UnwindSafe for RLComponents<RLC>
impl<RLC> Freeze for RLComponents<RLC>where
Option<RLCheckpointer<RLC>>: Freeze,
AsyncProcessorTraining<RLEvent<<RLC as RLComponentsTypes>::TrainingOutput, <RLC as RLComponentsTypes>::ActionContext>, AgentEvaluationEvent<<RLC as RLComponentsTypes>::ActionContext>>: Freeze,
impl<RLC> Send for RLComponents<RLC>where
Option<RLCheckpointer<RLC>>: Send,
AsyncProcessorTraining<RLEvent<<RLC as RLComponentsTypes>::TrainingOutput, <RLC as RLComponentsTypes>::ActionContext>, AgentEvaluationEvent<<RLC as RLComponentsTypes>::ActionContext>>: Send,
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more
impl<ST, DT> CastableFrom<ST, Initialized, Initialized> for DT
impl<ST, DT> CastableFrom<ST, Uninit, Uninit> for DT
Source§impl<T> IntoEither for T
impl<T> IntoEither for T
Source§fn into_either(self, into_left: bool) -> Either<Self, Self> ⓘ
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 moreSource§fn into_either_with<F>(self, into_left: F) -> Either<Self, Self> ⓘ
fn into_either_with<F>(self, into_left: F) -> Either<Self, Self> ⓘ
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