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

Environments.Gym.ClassicControl.PendulumV0

Description

The inverted pendulum swingup problem is a classic problem in the control literature. In this version of the problem, the pendulum starts in a random position, and the goal is to swing it up so it stays upright.

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

Synopsis

Documentation

newtype Action Source #

Force to exert on the pendulum

Constructors

Action
Fields getAction :: Float

Instances

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 #
(MonadIO t, MonadThrow 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.PendulumV0" "reinforce-0.0.0.1-BYNakn0URySEY5wecxfdnO" True) (C1 (MetaCons "Action" PrefixI True) (S1 (MetaSel (Just Symbol "getAction") NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 Float)))

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

type alias of RunnerT in IO

data State Source #

State of a PendulumV0 environment FIXME: give these semantics or move to a tuple?

Constructors

State
Fields cosTheta :: Float sinTheta :: Float thetaDot :: 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] #
(MonadIO t, MonadThrow 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.PendulumV0" "reinforce-0.0.0.1-BYNakn0URySEY5wecxfdnO" False) (C1 (MetaCons "State" PrefixI True) ((::) (S1 (MetaSel (Just Symbol "cosTheta") NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 Float)) ((::) (S1 (MetaSel (Just Symbol "sinTheta") NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 Float)) (S1 (MetaSel (Just Symbol "thetaDot") 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 PendulumV0 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