pub enum ActorMode {
Training,
Evaluation,
}
Expand description
Behaviour mode of an actor.
Variants
Training
Training mode
A training-mode actor expects that its actions will be used as the basis for training data. It may take explicitly exploratory actions that are sub-optimal within an episode (given the agent’s current knowledge or abilities) but that potentially allow for better strategies to be discovered when learning over the course of multiple episodes.
Evaluation
Evaluation mode
An evaluation-mode actor attempts to maximize reward to the best of its ability in each episode. The actor may learn within an episode, including taking exploratory actions that it expects to yeild improved performace within that episode but should assume that no agent updates will be performed with resulting data.
Trait Implementations
sourceimpl<'de> Deserialize<'de> for ActorMode
impl<'de> Deserialize<'de> for ActorMode
sourcefn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error> where
__D: Deserializer<'de>,
fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error> where
__D: Deserializer<'de>,
Deserialize this value from the given Serde deserializer. Read more
impl Copy for ActorMode
impl Eq for ActorMode
impl StructuralEq for ActorMode
impl StructuralPartialEq for ActorMode
Auto Trait Implementations
impl RefUnwindSafe for ActorMode
impl Send for ActorMode
impl Sync for ActorMode
impl Unpin for ActorMode
impl UnwindSafe for ActorMode
Blanket Implementations
sourceimpl<T> BorrowMut<T> for T where
T: ?Sized,
impl<T> BorrowMut<T> for T where
T: ?Sized,
const: unstable · sourcefn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more
sourceimpl<Q, K> Equivalent<K> for Q where
Q: Eq + ?Sized,
K: Borrow<Q> + ?Sized,
impl<Q, K> Equivalent<K> for Q where
Q: Eq + ?Sized,
K: Borrow<Q> + ?Sized,
sourcefn equivalent(&self, key: &K) -> bool
fn equivalent(&self, key: &K) -> bool
Compare self to key
and return true
if they are equal.