Copyright | (c) Sentenai 2017 |
---|---|
License | BSD3 |
Maintainer | sam@sentenai.com |
Stability | experimental |
Safe Haskell | None |
Language | Haskell2010 |
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. Here, the reward is greater if you spend less energy to reach the > goal. > > MountainCarContinuous-v0 defines "solving" as getting average reward of > 90.0 over 100 consecutive trials. > > This problem was first described by Andrew Moore in his PhD thesis [Moore90]. > > Here, this is the continuous version.
- data Action
- type Runner s a x = RunnerT s a IO x
- data State = State {}
- type Environment = EnvironmentT IO
- type EnvironmentT t = GymEnvironmentT State Action t
- runEnvironment :: Manager -> BaseUrl -> RunnerT State Action IO x
- runEnvironmentT :: MonadIO t => Manager -> BaseUrl -> RunnerT State Action t x
- runDefaultEnvironment :: RunnerT State Action IO x
- runDefaultEnvironmentT :: MonadIO t => RunnerT State Action t x
Documentation
Actions a car can perform to get out of it's predicament
State of a car stuck between two hills
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