object Gradient extends Serializable
- Source
- Gradient.scala
- Alphabetic
- By Inheritance
- Gradient
- Serializable
- Serializable
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Type Members
-
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.
-
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
-
final
def
!=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
##(): Int
- Definition Classes
- AnyRef → Any
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
equals(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
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.
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
incrementalConfig(stepSize: Double, initial: Double = 0.0): Config[Double, AveragedValue]
Hand-selected version that uses AveragedValue to accumulate internally.
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
noBaseline(stepSize: Double): Config[Double, Unit]
Uses NO averaging baseline.
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toString(): String
- Definition Classes
- AnyRef → Any
-
final
def
wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
- object Item extends Serializable
edit this text on github
ScalaRL
This is the API documentation for the ScalaRL functional reinforcement learning library.
Further documentation for ScalaRL can be found at the documentation site.
Check out the ScalaRL package list for all the goods.