object Sweep
- Source
- Sweep.scala
- Alphabetic
- By Inheritance
- Sweep
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
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()
-
def
diffBelow[Obs, T](l: StateValueFn[Obs, T], r: StateValueFn[Obs, T], epsilon: Double)(combine: (Double, Double) ⇒ Double)(implicit arg0: ToDouble[T]): Boolean
Helper to tell if we can stop iterating.
Helper to tell if we can stop iterating. The combine function is used to aggregate the differences between the value functions for each observation... the final aggregated value must be less than epsilon to return true, false otherwise.
-
def
diffValue[Obs, T](l: StateValueFn[Obs, T], r: StateValueFn[Obs, T], combine: (Double, Double) ⇒ Double)(implicit T: ToDouble[T]): Double
TODO consider putting this on the actual trait.
-
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] )
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
- def isPolicyStable[Obs, A, R, T, M[_], S[_]](l: StateValueFn[Obs, T], r: StateValueFn[Obs, T], prepare: (R) ⇒ T, merge: (T, T) ⇒ T, states: Traversable[State[Obs, A, R, S]])(implicit arg0: DModule[T], arg1: Ordering[T], arg2: Expectation[S]): Boolean
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
def
sweep[Obs, A, R, T, M[_], S[_]](valueFn: StateValueFn[Obs, T], policyFn: (StateValueFn[Obs, T]) ⇒ Policy[Obs, A, R, M, S], evaluatorFn: (StateValueFn[Obs, T], Policy[Obs, A, R, M, S]) ⇒ StateValue[Obs, A, R, T, S], states: Traversable[State[Obs, A, R, S]], inPlace: Boolean, valueIteration: Boolean)(implicit arg0: Expectation[M], arg1: Expectation[S]): StateValueFn[Obs, T]
This sweeps across the whole state space and updates the policy every single time IF you set valueIteration to true.
This sweeps across the whole state space and updates the policy every single time IF you set valueIteration to true. Otherwise it creates a policy once and then uses it each time.
What we really want is the ability to ping between updates to the value function or learning steps; to insert them every so often.
This function does NOT currently return the final policy, since you can just make it yourself, given the return value and the function.
- def sweepUntil[Obs, A, R, T, M[_], S[_]](valueFn: StateValueFn[Obs, T], policyFn: (StateValueFn[Obs, T]) ⇒ Policy[Obs, A, R, M, S], evaluatorFn: (StateValueFn[Obs, T], Policy[Obs, A, R, M, S]) ⇒ StateValue[Obs, A, R, T, S], states: Traversable[State[Obs, A, R, S]], stopFn: (StateValueFn[Obs, T], StateValueFn[Obs, T], Long) ⇒ Boolean, inPlace: Boolean, valueIteration: Boolean)(implicit arg0: Expectation[M], arg1: Expectation[S]): (StateValueFn[Obs, T], Long)
-
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 Update 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.