Main Content

rlPrioritizedReplayMemory

Replay memory experience buffer with prioritized sampling

    Description

    An off-policy reinforcement learning agent stores experiences in a circular experience buffer. During training, the agent samples mini-batches of experiences from the buffer and uses these mini-batches to update its actor and critic function approximators.

    By default, built-in off-policy agents (DQN, DDPG, TD3, SAC, MBPO) use an rlReplayMemory object as their experience buffer. Agents uniformly sample data from this buffer. To perform nonuniform prioritized sampling [1], which can improve sample efficiency when training your agent, use an rlPrioritizedReplayMemory object. For more information on prioritized sampling, see Algorithms.

    Creation

    Description

    example

    buffer = rlPrioritizedReplayMemory(obsInfo,actInfo) creates a prioritized replay memory experience buffer that is compatible with the observation and action specifications in obsInfo and actInfo, respectively.

    buffer = rlPrioritizedReplayMemory(obsInfo,actInfo,maxLength) sets the maximum length of the buffer by setting the MaxLength property.

    Input Arguments

    expand all

    Observation specifications, specified as a reinforcement learning specification object or an array of specification objects defining properties such as dimensions, data types, and names of the observation signals.

    You can extract the observation specifications from an existing environment or agent using getObservationInfo. You can also construct the specifications manually using rlFiniteSetSpec or rlNumericSpec.

    Action specifications, specified as a reinforcement learning specification object defining properties such as dimensions, data types, and names of the action signals.

    You can extract the action specifications from an existing environment or agent using getActionInfo. You can also construct the specification manually using rlFiniteSetSpec or rlNumericSpec.

    Properties

    expand all

    This property is read-only.

    Maximum buffer length, specified as a positive integer.

    This property is read-only.

    Number of experiences in buffer, specified as a nonnegative integer.

    Priority exponent to control the impact of prioritization during probability computation, specified as a nonnegative scalar less than or equal to 1.

    If the priority exponent is zero, the agent uses uniform sampling.

    Initial value of the importance sampling exponent, specified as a nonnegative scalar less than or equal to 1

    Number of annealing steps for updating the importance sampling exponent, specified as a positive integer.

    This property is read-only.

    Current value of the importance sampling exponent, specified as a nonnegative scalar less than or equal to 1.

    During training, ImportanceSamplingExponent is linearly increased from InitialImportanceSamplingExponent to 1 over NumAnnealingSteps steps.

    Object Functions

    appendAppend experiences to replay memory buffer
    sampleSample experiences from replay memory buffer
    resizeResize replay memory experience buffer
    allExperiencesReturn all experiences in replay memory buffer
    getActionInfoObtain action data specifications from reinforcement learning environment, agent, or experience buffer
    getObservationInfoObtain observation data specifications from reinforcement learning environment, agent, or experience buffer
    resetReset environment, agent, experience buffer, or policy object

    Examples

    collapse all

    Create an environment for training the agent. For this example, load a predefined environment.

    env = rlPredefinedEnv("SimplePendulumWithImage-Discrete");

    Extract the observation and action specifications from the agent.

    obsInfo = getObservationInfo(env);
    actInfo = getActionInfo(env);

    Create a DQN agent from the environment specifications.

    agent = rlDQNAgent(obsInfo,actInfo);

    By default, the agent uses a replay memory experience buffer with uniform sampling.

    Replace the default experience buffer with a prioritized replay memory buffer.

    agent.ExperienceBuffer = rlPrioritizedReplayMemory(obsInfo,actInfo);

    Configure the prioritized replay memory options. For example, set the initial importance sampling exponent to 0.5 and the number of annealing steps for updating the exponent during training to 1e4.

    agent.ExperienceBuffer.NumAnnealingSteps = 1e4;
    agent.ExperienceBuffer.PriorityExponent = 0.5;
    agent.ExperienceBuffer.InitialImportanceSamplingExponent = 0.5;

    Limitations

    • Prioritized experience replay does not support agents that use recurrent neural networks.

    Algorithms

    Prioritized replay memory samples experiences according to experience priorities. For a given experience, the priority is defined as the absolute value of the associated temporal difference (TD) error. A larger TD error indicates that the critic network is not well-trained for the corresponding experience. Therefore, sampling such experiences during critic updates can help efficiently improve the critic performance, which often improves the sample efficiency of agent training.

    When using prioritized replay memory, agents use the following process when sampling a mini-batch of experiences and updating a critic.

    1. Compute the sampling probability P for each experience in the buffer based on the experience priority.

      P(j)=p(j)αi=1Np(i)α

      Here:

      • N is the number of experiences in the replay memory buffer

      • p is the experience priority.

      • α is a priority exponent. To set α, use the PriorityExponent parameter.

    2. Sample a mini-batch of experiences according to the computed probabilities.

    3. Compute the importance sampling weights (w) for the sampled experiences.

      w'(j)=(NP(j))βw(j)w'(j)maximini-batchw'(i)

      Here, β is the importance sampling exponent. The ImportanceSamplingExponent parameter contains the current value of β. To control β, set the ImportanceSamplingExponent and NumAnnealingSteps parameters.

    4. Compute the weighted loss using the importance sampling weights w and the TD error δ to update a critic

    5. Update the priorities of the sampled experiences based on the TD error.

      p(j)=|δ|

    6. Update the importance sampling exponent β by linearly annealing the exponent value until it reaches 1.

      ββ+1β0NS

      Here:

      • β0 is the initial importance sampling exponent. To specify β0, use the InitialImportanceSamplingExponent parameter.

      • NS is the number of annealing steps. To specify Ns, use the NumAnnealingSteps parameter.

    References

    [1] Schaul, Tom, John Quan, Ioannis Antonoglou, and David Silver. 'Prioritized experience replay'. arXiv:1511.05952 [Cs] 25 February 2016. https://arxiv.org/abs/1511.05952.

    Version History

    Introduced in R2022b