Main Content

rlQAgentOptions

Options for Q-learning agent

Description

Use an rlQAgentOptions object to specify options for creating Q-learning agents. To create a Q-learning agent, use rlQAgent

For more information on Q-learning agents, see Q-Learning Agents.

For more information on the different types of reinforcement learning agents, see Reinforcement Learning Agents.

Creation

Description

opt = rlQAgentOptions creates an rlQAgentOptions object for use as an argument when creating a Q-learning agent using all default settings. You can modify the object properties using dot notation.

opt = rlQAgentOptions(Name=Value) creates the options set opt and sets its properties using one or more name-value arguments. For example, rlQAgentOptions(DiscountFactor=0.95) creates an option set with a discount factor of 0.95. You can specify multiple name-value arguments.

Properties

expand all

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

Within a Simulink® environment, the RL Agent block in which the agent is specified to execute 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 agent is executed every time the environment advances. In this case, SampleTime is the time interval between consecutive elements in the output experience returned by sim or train. If SampleTime is -1, the time interval between consecutive elements in the returned output experience reflects the timing of the event that triggers the agent execution.

This property is shared between the agent and the agent options object within the agent. Therefore, if you change it in the agent options object, it gets changed in the agent, and vice versa.

Example: SampleTime=-1

Discount factor applied to future rewards during training, specified as a positive scalar less than or equal to 1.

Example: DiscountFactor=0.9

Options for epsilon-greedy exploration, specified as an EpsilonGreedyExploration object with the following properties.

PropertyDescriptionDefault Value
EpsilonProbability threshold to either randomly select an action or select the action that maximizes the state-action value function. A larger value of Epsilon means that the agent randomly explores the action space at a higher rate.1
EpsilonMinMinimum value of Epsilon0.01
EpsilonDecayDecay rate0.0050

At each interaction with the environment (that is at each training step) if Epsilon is greater than EpsilonMin, then it is updated using the following formula.

Epsilon = Epsilon*(1-EpsilonDecay)

Note that Epsilon is conserved between the end of an episode and the start of the next one. Therefore, it keeps on uniformly decreasing over multiple episodes until it reaches EpsilonMin.

If your agent converges on local optima too quickly, you can promote agent exploration by increasing Epsilon.

To specify exploration options, use dot notation after creating the rlQAgentOptions object opt. For example, set the epsilon value to 0.9.

opt.EpsilonGreedyExploration.Epsilon = 0.9;

Critic optimizer options, specified as an rlOptimizerOptions object. It allows you to specify training parameters of the critic approximator such as learning rate, gradient threshold, as well as the optimizer algorithm and its parameters. For more information, see rlOptimizerOptions and rlOptimizer.

Example: CriticOptimizerOptions = rlOptimizerOptions(LearnRate=5e-3)

Options to save additional agent data, specified as a structure containing the following fields.

  • Optimizer

  • PolicyState

You can save an agent object in one of the following ways:

  • Using the save command

  • Specifying saveAgentCriteria and saveAgentValue in an rlTrainingOptions object

  • Specifying an appropriate logging function within a FileLogger object.

When you save an agent using any method, the fields in the InfoToSave structure determine whether the corresponding data is saved with the agent. For example, if you set the Optimizer field to true, then the critic optimizer is saved along with the agent.

You can modify the InfoToSave property only after the agent options object is created.

Example: options.InfoToSave.Optimizer=true

Option to save the critic optimizer, specified as a logical value. For example, if you set the Optimizer field to false, then the critic optimizer (which is a hidden property of the agent and can contain internal states) is not saved along with the agent, therefore saving disk space and memory. However, when the optimizers contains internal states, the state of the saved agent is not identical to the state of the original agent.

Example: true

Option to save the state of the explorative policy, specified as a logical value. If you set the PolicyState field to false, then the state of the explorative policy (which is a hidden agent property) is not saved along with the agent. In this case, the state of the saved agent is not identical to the state of the original agent.

Example: true

Object Functions

rlQAgentQ-learning reinforcement learning agent

Examples

collapse all

Create a rlQAgentOptions object that specifies the agent sample time.

opt = rlQAgentOptions(SampleTime=0.5)
opt = 
  rlQAgentOptions with properties:

                  SampleTime: 0.5000
              DiscountFactor: 0.9900
    EpsilonGreedyExploration: [1x1 rl.option.EpsilonGreedyExploration]
      CriticOptimizerOptions: [1x1 rl.option.rlOptimizerOptions]
                  InfoToSave: [1x1 struct]

You can modify options using dot notation. For example, set the agent discount factor to 0.95.

opt.DiscountFactor = 0.95;

Version History

Introduced in R2019a