pub struct Ppo<M, O = COptimizer> { /* private fields */ }
Expand description
Proximal Policy Optimization (PPO) with a clipped objective.
Reference
“Proximal Policy Optimization Algorithms” by Schulman et al.
Trait Implementations
sourceimpl<'de, M, O> Deserialize<'de> for Ppo<M, O> where
M: Deserialize<'de>,
O: Deserialize<'de>,
impl<'de, M, O> Deserialize<'de> for Ppo<M, O> where
M: Deserialize<'de>,
O: Deserialize<'de>,
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
sourceimpl<M, O> Policy for Ppo<M, O> where
M: Module + SeqPacked + SeqIterative,
O: Optimizer,
impl<M, O> Policy for Ppo<M, O> where
M: Module + SeqPacked + SeqIterative,
O: Optimizer,
type PolicyModule = M
sourcefn update<AS: ParameterizedDistributionSpace<Tensor> + ?Sized>(
&mut self,
features: &dyn HistoryFeatures,
advantages: PackedTensor,
action_space: &AS,
logger: &mut dyn StatsLogger
)
fn update<AS: ParameterizedDistributionSpace<Tensor> + ?Sized>(
&mut self,
features: &dyn HistoryFeatures,
advantages: PackedTensor,
action_space: &AS,
logger: &mut dyn StatsLogger
)
Update the policy module. Read more
sourcefn actor<OS, AS>(
&self,
observation_space: NonEmptyFeatures<OS>,
action_space: AS
) -> PolicyActor<OS, AS, Self::Module>
fn actor<OS, AS>(
&self,
observation_space: NonEmptyFeatures<OS>,
action_space: AS
) -> PolicyActor<OS, AS, Self::Module>
Create an actor for the policy module.
impl<M: Copy, O: Copy> Copy for Ppo<M, O>
impl<M, O> StructuralPartialEq for Ppo<M, O>
Auto Trait Implementations
impl<M, O> RefUnwindSafe for Ppo<M, O> where
M: RefUnwindSafe,
O: RefUnwindSafe,
impl<M, O> Send for Ppo<M, O> where
M: Send,
O: Send,
impl<M, O> Sync for Ppo<M, O> where
M: Sync,
O: Sync,
impl<M, O> Unpin for Ppo<M, O> where
M: Unpin,
O: Unpin,
impl<M, O> UnwindSafe for Ppo<M, O> where
M: UnwindSafe,
O: UnwindSafe,
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