主要内容

rlNumericSpec

创造continuous action or observation data specifications for reinforcement learning environments

expand all in page

Description

AnrlNumericSpecobject specifies continuous action or observation data specifications for reinforcement learning environments.

Creation

Syntax

spec = rlNumericSpec(dimension)
spec = rlNumericSpec(dimension,Name,Value)

Description

example

spec= rlNumericSpec(方面)creates a data specification for continuous actions or observations and sets theDimensionproperty.

spec= rlNumericSpec(方面,Name,Value)setsPropertiesusing name-value pair arguments.

Properties

expand all

Lower limit of the data space, specified as a scalar or matrix of the same size as the data space. When下限is specified as a scalar,rlNumericSpec将其应用于数据空间中的所有条目。

Upper limit of the data space, specified as a scalar or matrix of the same size as the data space. WhenUpperLimitis specified as a scalar,rlNumericSpec将其应用于数据空间中的所有条目。

的名字rlNumericSpecobject, specified as a string.

Description of therlNumericSpecobject, specified as a string.

This property is read-only.

数据空间的维度，指定为数字向量。

This property is read-only.

有关数据类型的信息, specified as a string.

Object Functions

rlSimulinkEnv 使用实施的动态模型创建强化学习环境金宝app
rlfunctionenv Specify custom reinforcement learning environment dynamics using functions
rlRepresentation (Not recommended) Model representation for reinforcement learning agents

Examples

collapse all

This example uses:

打开实时脚本

对于这个示例,考虑rlSimplePendulumModel金宝appSimulink模型。该模型是一种简单的无摩擦摆，最初悬挂在向下的位置。

Open the model.

mdl ='rlsimplependulummodel'; open_system(mdl)

创造rlNumericSpec和rlFiniteSetSpec观察和行动信息的对象。

obsinfo = rlnumericspec（[3 1]）3个观测值的矢量​​：sin（theta），cos（theta），d（theta）/dt
obsInfo = rlNumericSpec with properties: LowerLimit: -Inf UpperLimit: Inf Name: [0x0 string] Description: [0x0 string] Dimension: [3 1] DataType: "double"
actInfo = rlFiniteSetSpec([-2 0 2])% 3 possible values for torque: -2 Nm, 0 Nm and 2 Nm
actInfo = rlFiniteSetSpec with properties: Elements: [3x1 double] Name: [0x0 string] Description: [0x0 string] Dimension: [1 1] DataType: "double"

You can use dot notation to assign property values for therlNumericSpec和rlFiniteSetSpecobjects.

obsInfo.Name ='observations'; actInfo.Name ='torque';

Assign the agent block path information, and create the reinforcement learning environment for the Simulink model using the information extracted in the previous steps.

AgentBlk = [MDL' / RL代理']; env = rlSimulinkEnv(mdl,agentBlk,obsInfo,actInfo)
env = SimulinkEnvWithAgent with properties: Model : rlSimplePendulumModel AgentBlock : rlSimplePendulumModel/RL Agent ResetFcn : [] UseFastRestart : on

You can also include a reset function using dot notation. For this example, randomly initializetheta0in the model workspace.

env.ResetFcn = @(in) setVariable(in,'theta0',randn,'Workspace'，MDL）
env = SimulinkEnvWithAgent with properties: Model : rlSimplePendulumModel AgentBlock : rlSimplePendulumModel/RL Agent ResetFcn : @(in)setVariable(in,'theta0',randn,'Workspace',mdl) UseFastRestart : on

版本History

Introduced in R2019a

See Also

||||||||

Topics