Main Content


Policy object to generate discrete max-Q actions for custom training loops and application deployment


    This object implements a max-Q policy, which returns the action that maximizes a discrete action-space Q-value function, given an input observation. You can create an rlMaxQPolicy object from an rlQValueFunction or rlVectorQValueFunction object, or extract it from an rlQAgent, rlDQNAgent or rlSARSAAgent. You can then train the policy object using a custom training loop or deploy it for your application using generatePolicyBlock or generatePolicyFunction. This policy is always deterministic and does not perform any exploration. For more information on policies and value functions, see Create Policies and Value Functions.




    policy = rlMaxQPolicy(qValueFunction) creates the max-Q policy object policy from the discrete action-space Q-value function qValueFunction. It also sets the QValueFunction property of policy to the input argument qValueFunction.


    expand all

    Discrete action-space Q-value function approximator, specified as an rlQValueFunction or rlVectorQValueFunction object.

    Observation specifications, specified as an rlFiniteSetSpec or rlNumericSpec object or an array of such objects. These objects define properties such as the dimensions, data types, and names of the observation signals.

    Action specifications, specified as an rlFiniteSetSpec object. This object defines the properties of the environment action channel, such as its dimensions, data type, and name. Note that the name of the action channel specified in actionInfo (if any) is not used.


    Only one action channel is allowed.

    Sample time of policy, specified as a positive scalar or as -1 (default). Setting this parameter to -1 allows for event-based simulations.

    Within a Simulink® environment, the RL Agent block in which the policy is specified executes every SampleTime seconds of simulation time. If SampleTime is -1, the block inherits the sample time from its parent subsystem.

    Within a MATLAB® environment, the policy is executed every time the environment advances. In this case, SampleTime is the time interval between consecutive elements in the output experience. If SampleTime is -1, the sample time is treated as being equal to 1.

    Example: 0.2

    Object Functions

    generatePolicyBlockGenerate Simulink block that evaluates policy of an agent or policy object
    generatePolicyFunctionGenerate function that evaluates policy of an agent or policy object
    getActionObtain action from agent, actor, or policy object given environment observations
    getLearnableParametersObtain learnable parameter values from agent, function approximator, or policy object
    resetReset environment, agent, experience buffer, or policy object
    setLearnableParametersSet learnable parameter values of agent, function approximator, or policy object


    collapse all

    Create observation and action specification objects. For this example, define the observation space as a continuous four-dimensional space, so that a single observation is a column vector containing four doubles, and the action space as a finite set consisting of two possible values, -1 and 1.

    obsInfo = rlNumericSpec([4 1]);
    actInfo = rlFiniteSetSpec([-1 1]);

    Alternatively, you can use getObservationInfo and getActionInfo to extract the specification objects from an environment.

    Create a vector Q-value function approximator to use as critic. A vector Q-value function must accept an observation as input and return a single vector with as many elements as the number of possible discrete actions.

    To approximate the vector Q-value function within the critic, use a neural network. Define a single path from the network input to its output as an array of layer objects.

    layers = [ 

    Convert the network to a dlnetwork object and display the number of weights.

    model = dlnetwork(layers);
       Initialized: true
       Number of learnables: 72
          1   'input'   4 features

    Create a vector Q-value function using model, and the observation and action specifications.

    qValueFcn = rlVectorQValueFunction(model,obsInfo,actInfo)
    qValueFcn = 
      rlVectorQValueFunction with properties:
        ObservationInfo: [1x1 rl.util.rlNumericSpec]
             ActionInfo: [1x1 rl.util.rlFiniteSetSpec]
              UseDevice: "cpu"

    Check the critic with a random observation input.

    ans = 2x1 single column vector

    Create a policy object from qValueFcn.

    policy = rlMaxQPolicy(qValueFcn)
    policy = 
      rlMaxQPolicy with properties:
         QValueFunction: [1x1 rl.function.rlVectorQValueFunction]
        ObservationInfo: [1x1 rl.util.rlNumericSpec]
             ActionInfo: [1x1 rl.util.rlFiniteSetSpec]
             SampleTime: -1

    Check the policy with a random observation input.

    ans = 1x1 cell array

    You can now train the policy with a custom training loop and then deploy it to your application.

    Version History

    Introduced in R2022a