package state
Ordering
- Alphabetic
Visibility
- Public
- All
Type Members
-
case class
MapState[Obs, A, R, S[_]](observation: Obs, rewards: Map[A, S[R]], penalty: S[R], step: (Obs, A, R, S[R]) ⇒ (Obs, S[R]))(implicit evidence$2: Functor[S]) extends State[Obs, A, R, S] with Product with Serializable
MDP with a single state.
-
case class
StaticMapState[A, R, S[_]](rewards: Map[A, S[R]], penalty: S[R])(implicit evidence$1: Functor[S]) extends State[Unit, A, R, S] with Product with Serializable
MapState that doesn't evolve.
-
case class
TickState[Obs, A, R, S[_]](state: State[Obs, A, R, S], tick: Int, limit: Int)(implicit evidence$1: Functor[S]) extends State[Obs, A, R, S] with Product with Serializable
State that ends after a certain number of interactions.
State that ends after a certain number of interactions. This is useful for turning a non-episodic into an episodic task.
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.