Copyright	(c) Sentenai 2017
License	BSD3
Maintainer	sam@sentenai.com
Stability	experimental
Safe Haskell	None
Language	Haskell2010

Environments.Gym.ClassicControl.MountainCarV0

Description

Environment description: > A car is on a one-dimensional track, positioned between two "mountains". > The goal is to drive up the mountain on the right; however, the car's > engine is not strong enough to scale the mountain in a single pass. > Therefore, the only way to succeed is to drive back and forth to build up > momentum. > > MountainCar-v0 defines "solving" as getting average reward of -110.0 over > 100 consecutive trials. > > This problem was first described by Andrew Moore in his PhD thesis > [Moore90].

https://gym.openai.com/envs/MountainCar-v0

Synopsis

Documentation

data Action Source #

Actions a car can perform to get out of it's predicament

Constructors

MoveLeft
DoNothing
MoveRight

Instances

Bounded Action Source #
Methods minBound :: Action # maxBound :: Action #
Enum Action Source #
Methods succ :: Action -> Action # pred :: Action -> Action # toEnum :: Int -> Action # fromEnum :: Action -> Int # enumFrom :: Action -> [Action] # enumFromThen :: Action -> Action -> [Action] # enumFromTo :: Action -> Action -> [Action] # enumFromThenTo :: Action -> Action -> Action -> [Action] #
Eq Action Source #
Methods (==) :: Action -> Action -> Bool # (/=) :: Action -> Action -> Bool #
Ord Action Source #
Methods compare :: Action -> Action -> Ordering # (<) :: Action -> Action -> Bool # (<=) :: Action -> Action -> Bool # (>) :: Action -> Action -> Bool # (>=) :: Action -> Action -> Bool # max :: Action -> Action -> Action # min :: Action -> Action -> Action #
Show Action Source #
Methods showsPrec :: Int -> Action -> ShowS # show :: Action -> String # showList :: [Action] -> ShowS #
Generic Action Source #
Associated Types type Rep Action :: * -> * # Methods from :: Action -> Rep Action x # to :: Rep Action x -> Action #
Hashable Action Source #
Methods hashWithSalt :: Int -> Action -> Int # hash :: Action -> Int #
ToJSON Action Source #
Methods toJSON :: Action -> Value # toEncoding :: Action -> Encoding # toJSONList :: [Action] -> Value # toEncodingList :: [Action] -> Encoding #
(MonadThrow t, MonadIO t) => MonadEnv (EnvironmentT t) State Action Reward Source #
Methods reset :: EnvironmentT t (Initial State) Source # step :: Action -> EnvironmentT t (Obs Reward State) Source #
type Rep Action Source #
type Rep Action = D1 (MetaData "Action" "Environments.Gym.ClassicControl.MountainCarV0" "reinforce-0.0.0.1-BYNakn0URySEY5wecxfdnO" False) ((:+:) (C1 (MetaCons "MoveLeft" PrefixI False) U1) ((:+:) (C1 (MetaCons "DoNothing" PrefixI False) U1) (C1 (MetaCons "MoveRight" PrefixI False) U1)))

type Runner s a x = RunnerT s a IO x Source #

type alias of RunnerT in IO

data State Source #

State of a car stuck between two hills

Constructors

State
Fields position :: Float velocity :: Float

Instances

Eq State Source #
Methods (==) :: State -> State -> Bool # (/=) :: State -> State -> Bool #
Ord State Source #
Methods compare :: State -> State -> Ordering # (<) :: State -> State -> Bool # (<=) :: State -> State -> Bool # (>) :: State -> State -> Bool # (>=) :: State -> State -> Bool # max :: State -> State -> State # min :: State -> State -> State #
Show State Source #
Methods showsPrec :: Int -> State -> ShowS # show :: State -> String # showList :: [State] -> ShowS #
Generic State Source #
Associated Types type Rep State :: * -> * # Methods from :: State -> Rep State x # to :: Rep State x -> State #
Hashable State Source #
Methods hashWithSalt :: Int -> State -> Int # hash :: State -> Int #
FromJSON State Source #
Methods parseJSON :: Value -> Parser State # parseJSONList :: Value -> Parser [State] #
(MonadThrow t, MonadIO t) => MonadEnv (EnvironmentT t) State Action Reward Source #
Methods reset :: EnvironmentT t (Initial State) Source # step :: Action -> EnvironmentT t (Obs Reward State) Source #
type Rep State Source #
type Rep State = D1 (MetaData "State" "Environments.Gym.ClassicControl.MountainCarV0" "reinforce-0.0.0.1-BYNakn0URySEY5wecxfdnO" False) (C1 (MetaCons "State" PrefixI True) ((:*:) (S1 (MetaSel (Just Symbol "position") NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 Float)) (S1 (MetaSel (Just Symbol "velocity") NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 Float))))

type Environment = EnvironmentT IO Source #

Alias to EnvironmentT in IO

type EnvironmentT t = GymEnvironmentT State Action t Source #

Alias to GymEnvironmentT with MountainCarV0 type dependencies

runEnvironment :: Manager -> BaseUrl -> RunnerT State Action IO x Source #

Alias to runEnvironment in IO

runEnvironmentT :: MonadIO t => Manager -> BaseUrl -> RunnerT State Action t x Source #

Alias to runEnvironmentT

runDefaultEnvironment :: RunnerT State Action IO x Source #

Alias to runDefaultEnvironment in IO

runDefaultEnvironmentT :: MonadIO t => RunnerT State Action t x Source #

Alias to runDefaultEnvironmentT