rlFiniteSetSpec

Create discrete action or observation data specifications for reinforcement learning environments

Description

An rlFiniteSetSpec object specifies discrete action or observation data specifications for reinforcement learning environments.

Creation

Syntax

spec = rlFiniteSetSpec(elements)

Description

spec = rlFiniteSetSpec(elements) creates a data specification with a discrete set of actions or observations, setting the Elements property.

Properties

Elements — Set of valid actions or observations

vector | cell array

Set of valid actions or observations for the environment, specified as one of the following:

• Vector — Specify valid numeric values for a single action or single observation.

• Cell array — Specify valid numeric value combinations when you have more than one action or observation. Each entry of the cell array must have the same dimensions.

Name — Name of the rlFiniteSetSpec object

string (default)

Name of the rlFiniteSetSpec object, specified as a string. Use this property to set a meaningful name for your finite set.

Description — Description of the rlFiniteSetSpec object

string (default)

Description of the rlFiniteSetSpec object, specified as a string. Use this property to specify a meaningful description of the finite set values.

Dimension — Size of each element

vector (default)

This property is read-only.

Size of each element, specified as a vector.

If you specify Elements as a vector, then Dimension is [1 1]. Otherwise, if you specify a cell array, then Dimension indicates the size of the entries in Elements.

DataType — Information about the type of data

string (default)

This property is read-only.

Information about the type of data, specified as a string.

Object Functions

rlSimulinkEnv	Create reinforcement learning environment using dynamic model implemented in Simulink
rlFunctionEnv	Specify custom reinforcement learning environment dynamics using functions
rlRepresentation	(Not recommended) Model representation for reinforcement learning agents

Examples

Reinforcement Learning Environment for Simulink Model

For this example, consider the rlSimplePendulumModel Simulink model. The model is a simple frictionless pendulum that is initially hanging in a downward position.

Open the model.

mdl = 'rlSimplePendulumModel';
open_system(mdl)

Create rlNumericSpec and rlFiniteSetSpec objects for the observation and action information, respectively.

obsInfo = rlNumericSpec([3 1]) % vector of 3 observations: 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 the rlNumericSpec and rlFiniteSetSpec objects.

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

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

agentBlk = [mdl '/RL Agent'];
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 initialize theta0 in 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

Specify Discrete Value Set for Multiple Actions

If the actor for your reinforcement learning agent has multiple outputs, each with a discrete action space, you can specify the possible discrete actions combinations using an rlFiniteSetSpec object.

Suppose that the valid values for a two-output system are [1 2] for the first output and [10 20 30] for the second output. Create a discrete action space specification for all possible input combinations.

actionSpec = rlFiniteSetSpec({[1 10],[1 20],[1 30],...
                              [2 10],[2 20],[2 30]})

actionSpec = 
  rlFiniteSetSpec with properties:

       Elements: {6x1 cell}
           Name: [0x0 string]
    Description: [0x0 string]
      Dimension: [1 2]
       DataType: "double"