Struct relearn::feedback::Reward

pub struct Reward(pub f64);

A reward-signal environment feedback

Tuple Fields

0: f64

Implementations

impl Reward

pub const fn unwrap(self) -> f64

Get the reward value as a float

Trait Implementations

impl Add<Reward> for Reward

type Output = Reward

The resulting type after applying the + operator.

fn add(self, rhs: Reward) -> Reward

Performs the + operation.

impl AddAssign<Reward> for Reward

fn add_assign(&mut self, rhs: Reward)

Performs the += operation.

impl Bounded for Reward

fn min_value() -> Self

Returns the smallest finite number this type can represent

fn max_value() -> Self

Returns the largest finite number this type can represent

impl Clone for Reward

fn clone(&self) -> Reward

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for Reward

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

Formats the value using the given formatter.

impl Default for Reward

fn default() -> Reward

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for Reward

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

Deserialize this value from the given Serde deserializer.

impl Display for Reward

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

Formats the value using the given formatter.

impl Feedback for Reward

type EpisodeFeedback = Reward

Overall feedback for an episode.

type StepSummary = RewardSummary

Per-step feedback summary.

type EpisodeSummary = RewardSummary

Per-episode feedback summary.

fn add_to_episode_feedback(&self, episode_feedback: &mut Self::EpisodeFeedback)

impl From<Reward> for f64

fn from(Reward: Reward) -> Self

Converts to this type from the input type.

impl From<f64> for Reward

fn from(r: f64) -> Self

Converts to this type from the input type.

impl Loggable for Reward

fn log<L: StatsLogger + ?Sized>(
    &self,
    name: &'static str,
    logger: &mut L
) -> Result<(), LogError>

impl MetaFeedback for Reward

Reward feedback is always replicated in both the inner and outer environments.

This is the structure of RL-Squared meta reinforcement learning.

type Inner = Reward

type Outer = Reward

fn neutral_outer() -> Self

Neutral outer feedback that does not indicate good or bad behaviour.

fn into_inner_outer(self) -> (Self, Self)

Split the feedback into inner and outer environment feedback

impl PartialEq<Reward> for Reward

fn eq(&self, other: &Reward) -> bool

This method tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Reward) -> bool

This method tests for !=.

impl PartialOrd<Reward> for Reward

fn partial_cmp(&self, other: &Reward) -> Option<Ordering>

This method returns an ordering between self and other values if one exists.

fn lt(&self, other: &Rhs) -> bool

This method tests less than (for self and other) and is used by the < operator.

fn le(&self, other: &Rhs) -> bool

This method tests less than or equal to (for self and other) and is used by the <= operator.

fn gt(&self, other: &Rhs) -> bool

This method tests greater than (for self and other) and is used by the > operator.

fn ge(&self, other: &Rhs) -> bool

This method tests greater than or equal to (for self and other) and is used by the >= operator.

impl Serialize for Reward

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

Serialize this value into the given Serde serializer.

impl Sub<Reward> for Reward

type Output = Reward

The resulting type after applying the - operator.

fn sub(self, rhs: Reward) -> Reward

Performs the - operation.

impl SubAssign<Reward> for Reward

fn sub_assign(&mut self, rhs: Reward)

Performs the -= operation.

impl ToPrimitive for Reward

fn to_i64(&self) -> Option<i64>

Converts the value of self to an i64. If the value cannot be represented by an i64, then None is returned.

fn to_u64(&self) -> Option<u64>

Converts the value of self to a u64. If the value cannot be represented by a u64, then None is returned.

fn to_f32(&self) -> Option<f32>

Converts the value of self to an f32. Overflows may map to positive or negative inifinity, otherwise None is returned if the value cannot be represented by an f32.

fn to_f64(&self) -> Option<f64>

Converts the value of self to an f64. Overflows may map to positive or negative inifinity, otherwise None is returned if the value cannot be represented by an f64.

fn to_isize(&self) -> Option<isize>

Converts the value of self to an isize. If the value cannot be represented by an isize, then None is returned.

fn to_i8(&self) -> Option<i8>

Converts the value of self to an i8. If the value cannot be represented by an i8, then None is returned.

fn to_i16(&self) -> Option<i16>

Converts the value of self to an i16. If the value cannot be represented by an i16, then None is returned.

fn to_i32(&self) -> Option<i32>

Converts the value of self to an i32. If the value cannot be represented by an i32, then None is returned.

fn to_i128(&self) -> Option<i128>

Converts the value of self to an i128. If the value cannot be represented by an i128 (i64 under the default implementation), then None is returned.

fn to_usize(&self) -> Option<usize>

Converts the value of self to a usize. If the value cannot be represented by a usize, then None is returned.

fn to_u8(&self) -> Option<u8>

Converts the value of self to a u8. If the value cannot be represented by a u8, then None is returned.

fn to_u16(&self) -> Option<u16>

Converts the value of self to a u16. If the value cannot be represented by a u16, then None is returned.

fn to_u32(&self) -> Option<u32>

Converts the value of self to a u32. If the value cannot be represented by a u32, then None is returned.

fn to_u128(&self) -> Option<u128>

Converts the value of self to a u128. If the value cannot be represented by a u128 (u64 under the default implementation), then None is returned.

impl Copy for Reward

impl StructuralPartialEq for Reward