Main Content

rlDQNAgentOptions

Options for DQN agent

Description

Use an rlDQNAgentOptions object to specify options for deep Q-network (DQN) agents. To create a DQN agent, use rlDQNAgent.

For more information, see Deep Q-Network (DQN) Agents.

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

Creation

Description

opt = rlDQNAgentOptions creates an options object for use as an argument when creating a DQN agent using all default settings. You can modify the object properties using dot notation.

example

opt = rlDQNAgentOptions(Name=Value) creates the options set opt and sets its properties using one or more name-value arguments. For example, rlDQNAgentOptions(DiscountFactor=0.95) creates an options 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 rlDQNAgentOptions object opt. For example, set the epsilon value to 0.9.

opt.EpsilonGreedyExploration.Epsilon = 0.9;

Experience buffer size, specified as a positive integer. During training, the agent computes updates using a mini-batch of experiences randomly sampled from the buffer.

Example: ExperienceBufferLength=1e6

Size of random experience mini-batch, specified as a positive integer. During each training episode, the agent randomly samples experiences from the experience buffer when computing gradients for updating the critic properties. Large mini-batches reduce the variance when computing gradients but increase the computational effort.

When using a recurrent neural network for the critic, MiniBatchSize is the number of experience trajectories in a batch, where each trajectory has length equal to SequenceLength.

Example: MiniBatchSize=128

Maximum batch-training trajectory length when using a recurrent neural network, specified as a positive integer. This value must be greater than 1 when using a recurrent neural network and 1 otherwise.

Example: SequenceLength=4

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)

Number of future rewards used to estimate the value of the policy, specified as a positive integer. Specifically, ifNumStepsToLookAhead is equal to N, the target value of the policy at a given step is calculated adding the rewards for the following N steps and the discounted estimated value of the state that caused the N-th reward. This target is also called N-step return.

Note

When using a recurrent neural network for the critic, NumStepsToLookAhead must be 1.

For more information, see [1], Chapter 7.

Example: NumStepsToLookAhead=3

Minimum number of samples to generate before learning starts. Use this option to ensure that learning takes place over a more diverse data set at the beginning of training. The default, and minimum, value is the value of MiniBatchSize. After the software collects a minimum of NumWarmStartSteps samples, learning occurs at the intervals specified by the LearningFrequency property.

Example: NumWarmStartSteps=20

Number of times an agent learns over a data set, specified as a positive integer. For off-policy agents that support this property (DQN, DDPG, TD3 and SAC), this value defines the number of passes over the data in the replay buffer at each learning iteration.

Example: NumEpoch=2

Maximum number of mini-batches used for learning during a single epoch, specified as a positive integer.

For off-policy agents that support this property (DQN, DDPG, TD3, and SAC), the actual number of mini-batches used for learning depends on the length of the replay buffer, and MaxMiniBatchPerEpoch specifies the upper bound. This value also specifies the maximum number of gradient steps per learning iteration because the maximum number of gradient steps is equal to the MaxMiniBatchPerEpoch value multiplied by the NumEpoch value.

For off-policy agents that support this property, a high MaxMiniBatchPerEpoch value means that more time is spent on learning than collecting new data. Therefore, you can use this parameter to control the sample efficiency of the learning process.

Example: MaxMiniBatchPerEpoch=200

Minimum number of environment interactions between learning iterations, specified as a positive integer or -1. This value defines how many new data samples need to be generated before learning. For off-policy agents that support this property (DQN, DDPG, TD3, and SAC), the default value of -1 means that learning occurs after each episode is finished. Note that learning can start only after the software collects a minimum of NumWarmStartSteps samples. It then occurs at the intervals specified by the LearningFrequency property.

Example: LearningFrequency=4

Option to use double DQN for value function target updates, specified as a logical value. For more information, see Deep Q-Network (DQN) Agents.

Example: UseDoubleDQN=false

Smoothing factor for target critic updates, specified as a positive scalar less than or equal to 1. For more information, see Target Update Methods.

Example: TargetSmoothFactor=1e-2

Number of steps between target critic updates, specified as a positive integer. For more information, see Target Update Methods.

Example: TargetUpdateFrequency=5

Batch data regularizer options, specified as an rlBehaviorCloningRegularizerOptions object. These options are typically used to train the agent offline, from existing data. If you leave this option empty, no regularizer is used.

For more information, see rlBehaviorCloningRegularizerOptions.

Example: BatchDataRegularizerOptions = rlBehaviorCloningRegularizerOptions(BehaviorCloningRegularizerWeight=10)

Option for clearing the experience buffer before training, specified as a logical value.

Example: ResetExperienceBufferBeforeTraining=true

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

  • Optimizer

  • PolicyState

  • Target

  • ExperienceBuffer

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 actor and critic optimizers are 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 actor and critic optimizers, specified as a logical value. If you set the Optimizer field to false, then the actor and critic optimizers (which are hidden properties of the agent and can contain internal states) are 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

Option to save the actor and critic targets, specified as a logical value. If you set the Target field to false, then the actor and critic targets (which are hidden agent properties) is not saved along with the agent. In this case, when the targets contain internal states, the state of the saved agent is not identical to the state of the original agent.

Example: true

Option to save the experience buffer, specified as a logical value. If you set the PolicyState field to false, then the content of the experience buffer (which is accessible as an agent property using dot notation) 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

rlDQNAgentDeep Q-network (DQN) reinforcement learning agent

Examples

collapse all

Create an rlDQNAgentOptions object that specifies the agent mini-batch size.

opt = rlDQNAgentOptions(MiniBatchSize=48)
opt = 
  rlDQNAgentOptions with properties:

                             SampleTime: 1
                         DiscountFactor: 0.9900
               EpsilonGreedyExploration: [1x1 rl.option.EpsilonGreedyExploration]
                 ExperienceBufferLength: 10000
                          MiniBatchSize: 48
                         SequenceLength: 1
                 CriticOptimizerOptions: [1x1 rl.option.rlOptimizerOptions]
                    NumStepsToLookAhead: 1
                      NumWarmStartSteps: 48
                               NumEpoch: 1
                   MaxMiniBatchPerEpoch: 100
                      LearningFrequency: -1
                           UseDoubleDQN: 1
                     TargetSmoothFactor: 1.0000e-03
                  TargetUpdateFrequency: 1
            BatchDataRegularizerOptions: []
    ResetExperienceBufferBeforeTraining: 0
                             InfoToSave: [1x1 struct]

You can modify options using dot notation. For example, set the agent sample time to 0.5.

opt.SampleTime = 0.5;

References

[1] Sutton, Richard S., and Andrew G. Barto. Reinforcement Learning: An Introduction. Second edition. Adaptive Computation and Machine Learning. Cambridge, Mass: The MIT Press, 2018.

Version History

Introduced in R2019a

expand all