Packages

package bandit

Ordering
  1. Alphabetic
Visibility
  1. Public
  2. All

Type Members

  1. case class Gradient[Obs, A, R, T, S[_]](config: Config[R, T], valueFn: ActionValueFn[Obs, A, Item[T]])(implicit evidence$1: Equiv[A], evidence$2: ToDouble[R], evidence$3: ToDouble[T]) extends Policy[Obs, A, R, Cat, S] with Product with Serializable

    This thing needs to track its average reward internally...

    This thing needs to track its average reward internally... then, if we have the gradient baseline set, use that thing to generate the notes.

    T is the "average" type.

  2. case class Greedy[Obs, A, R, T, S[_]](config: Config[R, T], valueFn: ActionValueFn[Obs, A, T])(implicit evidence$1: Ordering[T]) extends Policy[Obs, A, R, Cat, S] with Product with Serializable

  3. case class UCB[Obs, A, R, T, S[_]](config: Config[R, T], valueFn: ActionValueFn[Obs, A, Choice[T]], time: Time) extends Policy[Obs, A, R, Cat, S] with Product with Serializable

Value Members

  1. object Gradient extends Serializable
  2. object Greedy extends Serializable
  3. object UCB extends Serializable

Ungrouped