rlFunctionEnv
Specify custom reinforcement learning environment dynamics using functions
Since R2019a
Description
Use rlFunctionEnv
to define a custom reinforcement learning
environment. You provide MATLAB® functions that define the step and reset behavior for the environment. This
object is useful when you want to customize your environment beyond the predefined
environments available with rlPredefinedEnv
.
Creation
Description
creates a reinforcement learning environment using the provided observation and action
specifications, env
= rlFunctionEnv(observationInfo
,actionInfo
,stepfcn
,resetfcn
)observationInfo
and actionInfo
,
respectively. You also set the StepFcn
and
ResetFcn
properties using MATLAB functions.
Input Arguments
Properties
Object Functions
getActionInfo | Obtain action data specifications from reinforcement learning environment, agent, or experience buffer |
getObservationInfo | Obtain observation data specifications from reinforcement learning environment, agent, or experience buffer |
train | Train reinforcement learning agents within a specified environment |
sim | Simulate trained reinforcement learning agents within specified environment |
validateEnvironment | Validate custom reinforcement learning environment |
Examples
Version History
Introduced in R2019a