Struct Bandit

pub struct Bandit<D> { /* private fields */ }

A multi-armed bandit

The distribution of each arm has type D.

Implementations

impl<D> Bandit<D>

pub fn new(distributions: Vec<D>) -> Self

impl<D: FromMean<f64>> Bandit<D>

pub fn from_means<I: IntoIterator<Item = T>, T: Borrow<f64>>( means: I, ) -> Result<Self, D::Error>

Create a new Bandit from a list of means.

impl Bandit<Bernoulli>

pub fn uniform<R: Rng>(num_arms: usize, rng: &mut R) -> Self

Create a new BernoulliBandit with uniform random means in [0, 1].

impl Bandit<Deterministic<f64>>

pub fn from_values<I: IntoIterator<Item = T>, T: Borrow<f64>>(values: I) -> Self

Create a new DeterministicBandit from a list of arm rewards

Trait Implementations

impl<D: Clone> Clone for Bandit<D>

fn clone(&self) -> Bandit<D>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<D: Debug> Debug for Bandit<D>

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

Formats the value using the given formatter.

impl<'de, D> Deserialize<'de> for Bandit<D>

where D: Deserialize<'de>,

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl<D: Bounded<f64>> EnvStructure for Bandit<D>

type ObservationSpace = SingletonSpace

type ActionSpace = IndexSpace

type FeedbackSpace = IntervalSpace<Reward>

fn observation_space(&self) -> Self::ObservationSpace

Space containing all possible observations.

fn action_space(&self) -> Self::ActionSpace

The space of all possible actions.

fn feedback_space(&self) -> Self::FeedbackSpace

The space of all possible feedback.

fn discount_factor(&self) -> f64

A discount factor applied to future feedback.

impl<D: Distribution<f64> + Bounded<f64>> Environment for Bandit<D>

type State = ()

Environment state type. Not necessarily observable by the agent.

type Observation = ()

Observation of the state provided to the agent.

type Action = usize

Action selected by the agent.

type Feedback = Reward

Feedback provided to a learning agent as the result of each step. Reward, for example.

fn initial_state(&self, _: &mut Prng) -> Self::State

Sample a state for the start of a new episode.

fn observe(&self, _: &Self::State, _: &mut Prng) -> Self::State

Generate an observation for a given state.

fn step( &self, _state: Self::State, action: &Self::Action, rng: &mut Prng, _logger: &mut dyn StatsLogger, ) -> (Successor<Self::State>, Self::Feedback)

Perform a state transition in reponse to an action.

fn run<T, L>( self, actor: T, seed: SimSeed, logger: L, ) -> Steps<Self, T, Prng, L>

where T: Actor<Self::Observation, Self::Action>, L: StatsLogger, Self: Sized,

Run this environment with the given actor.

impl<D: Hash> Hash for Bandit<D>

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl<D: PartialEq> PartialEq for Bandit<D>

fn eq(&self, other: &Bandit<D>) -> bool

Tests for self and other values to be equal, and is used by ==.

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

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl<D> Serialize for Bandit<D>

where D: Serialize,

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl<D: Clone> CloneBuild for Bandit<D>

impl<D: Eq> Eq for Bandit<D>

impl<D> StructuralPartialEq for Bandit<D>