Packages

object Gradient extends Serializable

Source
Gradient.scala
Linear Supertypes
Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. Gradient
  2. Serializable
  3. Serializable
  4. AnyRef
  5. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Type Members

  1. case class Config[R, T](initial: T, stepSize: Double, prepare: (R) ⇒ T, plus: (T, T) ⇒ T)(implicit evidence$7: ToDouble[R], evidence$8: ToDouble[T]) extends Product with Serializable

    Holds properties necessary to run the gradient algorithm.

  2. case class Item[T](q: Double, t: T) extends Product with Serializable

    Represents an action value AND some sort of accumulated value.

    Represents an action value AND some sort of accumulated value. The action value is something we get by aggregating a reward in some way.

    You might just sum, which would be goofy; you might do some averaged value, or exponentially decaying average.

    The t is the reward aggregator. The q is the item that's getting updated in this funky way.

    So how would you write a semigroup for this? You'd have to semigroup combine the T... what is the monoid on the q?

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int
    Definition Classes
    AnyRef → Any
  3. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  4. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  5. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  6. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  7. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  8. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  9. def fromAggregator[R, T](stepSize: Double, initial: T, agg: Aggregator[R, T, Double])(implicit arg0: ToDouble[R]): Config[R, T]

    Generate this gradient from some aggregator.

  10. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  11. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  12. def incrementalConfig(stepSize: Double, initial: Double = 0.0): Config[Double, AveragedValue]

    Hand-selected version that uses AveragedValue to accumulate internally.

  13. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  14. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  15. def noBaseline(stepSize: Double): Config[Double, Unit]

    Uses NO averaging baseline.

  16. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  17. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  18. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  19. def toString(): String
    Definition Classes
    AnyRef → Any
  20. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  21. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  22. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  23. object Item extends Serializable

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped