rlPPOAgentOptions
Options for PPO agent
Description
Use an rlPPOAgentOptions
object to specify options for proximal
policy optimization (PPO) agents. To create a PPO agent, use rlPPOAgent
.
For more information on PPO agents, see Proximal Policy Optimization (PPO) Agent.
For more information on the different types of reinforcement learning agents, see Reinforcement Learning Agents.
Creation
Description
creates an
opt
= rlPPOAgentOptionsrlPPOAgentOptions
object for use as an argument when creating a PPO
agent using all default settings. You can modify the object properties using dot
notation.
creates the options set opt
= rlPPOAgentOptions(Name=Value
)opt
and sets its properties using one
or more name-value arguments. For example,
rlPPOAgentOptions(DiscountFactor=0.95)
creates an option set with a
discount factor of 0.95
. You can specify multiple name-value
arguments.
Properties
SampleTime
— Sample time of agent
1
(default) | positive scalar | -1
Sample time of the agent, specified as a positive scalar or as -1
.
Within a MATLAB® environment, the agent is executed every time the environment advances,
so, SampleTime
does not affect the timing of the agent
execution.
Within a Simulink® environment, the RL Agent block
that uses the agent object executes every SampleTime
seconds of
simulation time. If SampleTime
is -1
the block
inherits the sample time from its input signals. Set SampleTime
to
-1
when the block is a child of an event-driven subsystem.
Note
Set SampleTime
to a positive scalar when the block is not
a child of an event-driven subsystem. Doing so ensures that the block executes
at appropriate intervals when input signal sample times change due to model
variations.
Regardless of the type of environment, the time interval between consecutive elements
in the output experience returned by sim
or
train
is
always SampleTime
.
If SampleTime
is -1
, for Simulink environments, the time interval between consecutive elements in the
returned output experience reflects the timing of the events that trigger the RL Agent block
execution, while for MATLAB environments, this time interval is considered equal to
1
.
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
DiscountFactor
— Discount factor
0.99
(default) | positive scalar less than or equal to 1
Discount factor applied to future rewards during training, specified as a positive scalar less than or equal to 1.
Example: DiscountFactor=0.9
EntropyLossWeight
— Entropy loss weight
0.01
(default) | scalar value between 0
and 1
Entropy loss weight, specified as a scalar value between 0
and 1
. A higher entropy loss weight value promotes agent
exploration by applying a penalty for being too certain about which action
to take. Doing so can help the agent move out of local optima.
When gradients are computed during training, an additional gradient component is computed for minimizing the entropy loss. For more information, see Entropy Loss.
Example: EntropyLossWeight=0.02
ExperienceHorizon
— Number of steps used to calculate the advantage
512
(default) | positive integer
Number of steps used to calculate the advantage, specified as a positive integer. For more information, see the agent training algorithm.
Example: ExperienceHorizon=1024
MiniBatchSize
— Mini-batch size
128
(default) | positive integer
Mini-batch size used for each learning epoch, specified as a positive integer. When the agent uses a recurrent neural network, MiniBatchSize
is treated as the training trajectory length.
The MiniBatchSize
value must be less than or equal to the ExperienceHorizon
value.
Example: MiniBatchSize=256
NumEpoch
— Number of times an agent learns over a data set of experiences
3
(default) | positive integer
Number of times an agent learns over a data set of experiences, specified as a
positive integer. This value defines the number of passes over a data set that has a
minimum length specified by the LearningFrequency
property.
Example: NumEpoch=2
MaxMiniBatchPerEpoch
— Maximum number of mini-batches used for learning during a single epoch
100
(default) | positive integer
Maximum number of mini-batches used for learning during a single epoch, specified as a positive integer.
For on-policy agents that support this property (PPO and TRPO), the actual number of
mini-batches used for learning depends on the length of aggregated trajectories, it has
a lower bound of
LearningFrequency
/MiniBatchSize
and an
upper bound of MaxMiniBatchPerEpoch
.
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 PPO and TRPO agents, it is good practice to
set this value to an arbitrarily high number to ensure all data is used for
training.
Example: MaxMiniBatchPerEpoch=500
LearningFrequency
— Minimum number of environment interactions between learning iterations
-1
(default) | positive integer
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 on-policy agents that support this property
(PPO and TRPO), set LearningFrequency
to an integer multiple of
MiniBatchSize
. The default value of -1
indicates that 10*MiniBatchSize
samples are collected before
learning. Set this property to a lower value (for example,
2*MiniBatchSize
) if you want the agent to learn more
frequently.
Example: LearningFrequency=4
ActorOptimizerOptions
— Actor optimizer options
rlOptimizerOptions
object
Actor optimizer options, specified as an rlOptimizerOptions
object. It allows you to specify training parameters of
the actor approximator such as learning rate, gradient threshold, as well as the
optimizer algorithm and its parameters. For more information, see rlOptimizerOptions
and rlOptimizer
.
Example: ActorOptimizerOptions =
rlOptimizerOptions(LearnRate=2e-3)
CriticOptimizerOptions
— Critic optimizer options
rlOptimizerOptions
object
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)
ClipFactor
— Clip factor
0.2
(default) | positive scalar less than 1
Clip factor for limiting the change in each policy update step, specified as a
positive scalar less than 1
.
Example: ClipFactor=0.5
AdvantageEstimateMethod
— Method for estimating advantage values
"gae"
(default) | "finite-horizon"
Method for estimating advantage values, specified as one of the following:
"gae"
— Generalized advantage estimator"finite-horizon"
— Finite horizon estimation
For more information on these methods, see the training algorithm information in Proximal Policy Optimization (PPO) Agent.
Example: AdvantageEstimateMethod="finite-horizon"
GAEFactor
— Smoothing factor for generalized advantage estimator
0.95
(default) | scalar value between 0
and 1
Smoothing factor for generalized advantage estimator, specified as a scalar value between 0
and 1
, inclusive. This option applies only when the AdvantageEstimateMethod
option is "gae"
Example: GAEFactor=0.97
NormalizedAdvantageMethod
— Method for normalizing advantage function
"none"
(default) | "current
| "moving"
Method for normalizing advantage function values, specified as one of the following:
"none"
— Do not normalize advantage values"current"
— Normalize the advantage function using the mean and standard deviation for the current mini-batch of experiences."moving"
— Normalize the advantage function using the mean and standard deviation for a moving window of recent experiences. To specify the window size, set theAdvantageNormalizingWindow
option.
In some environments, you can improve agent performance by normalizing the advantage function during training. The agent normalizes the advantage function by subtracting the mean advantage value and scaling by the standard deviation.
Example: NormalizedAdvantageMethod="moving"
AdvantageNormalizingWindow
— Window size for normalizing advantage function
1e6
(default) | positive integer
Window size for normalizing advantage function values, specified as a positive integer. Use this option when the NormalizedAdvantageMethod
option is "moving"
.
Example: AdvantageNormalizingWindow=1e5
InfoToSave
— Options to save additional agent data
structure (default)
Options to save additional agent data, specified as a structure containing a
field named Optimizer
.
You can save an agent object in one of the following ways:
Using the
save
commandSpecifying
saveAgentCriteria
andsaveAgentValue
in anrlTrainingOptions
objectSpecifying 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
Optimizer
— Option to save actor and critic optimizers
false
(default) | 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
contain internal states, the state of the saved
agent is not identical to the state of the original
agent.
Example: true
Object Functions
rlPPOAgent | Proximal policy optimization (PPO) reinforcement learning agent |
Examples
Create PPO Agent Options Object
Create a PPO agent options object, specifying the experience horizon.
opt = rlPPOAgentOptions(ExperienceHorizon=256)
opt = rlPPOAgentOptions with properties: SampleTime: 1 DiscountFactor: 0.9900 EntropyLossWeight: 0.0100 ExperienceHorizon: 256 MiniBatchSize: 128 NumEpoch: 3 MaxMiniBatchPerEpoch: 100 LearningFrequency: -1 ActorOptimizerOptions: [1x1 rl.option.rlOptimizerOptions] CriticOptimizerOptions: [1x1 rl.option.rlOptimizerOptions] ClipFactor: 0.2000 AdvantageEstimateMethod: "gae" GAEFactor: 0.9500 NormalizedAdvantageMethod: "none" AdvantageNormalizingWindow: 1000000 InfoToSave: [1x1 struct]
You can modify options using dot notation. For example, set the agent sample time to 0.5
.
opt.SampleTime = 0.5;
Version History
Introduced in R2019bR2024a: The NumEpoch
property changed behavior
The NumEpoch
property changed behavior. Previously, this property
defined the number of learning passes over a data set with minimum length of
ExperienceHorizon
. Now, it defines the number of passes over a data
set with minimum length of LearningFrequency
.
R2022a: Simulation and deployment: UseDeterministicExploitation
will be removed
The property UseDeterministicExploitation
of the
rlPPOAgentOptions
object will be removed in a future release. Use the
UseExplorationPolicy
property of rlPPOAgent
instead.
Previously, you set UseDeterministicExploitation
as follows.
Force the agent to always select the action with maximum likelihood, thereby using a greedy deterministic policy for simulation and deployment.
agent.AgentOptions.UseDeterministicExploitation = true;
Allow the agent to select its action by sampling its probability distribution for simulation and policy deployment, thereby using a stochastic policy that explores the observation space.
agent.AgentOptions.UseDeterministicExploitation = false;
Starting in R2022a, set UseExplorationPolicy
as follows.
Force the agent to always select the action with maximum likelihood, thereby using a greedy deterministic policy for simulation and deployment.
agent.UseExplorationPolicy = false;
Allow the agent to select its action by sampling its probability distribution for simulation and policy deployment, thereby using a stochastic policy that explores the observation space.
agent.UseExplorationPolicy = true;
Similarly to UseDeterministicExploitation
,
UseExplorationPolicy
affects only simulation and deployment; it does
not affect training.
Commande MATLAB
Vous avez cliqué sur un lien qui correspond à cette commande MATLAB :
Pour exécuter la commande, saisissez-la dans la fenêtre de commande de MATLAB. Les navigateurs web ne supportent pas les commandes MATLAB.
Select a Web Site
Choose a web site to get translated content where available and see local events and offers. Based on your location, we recommend that you select: .
You can also select a web site from the following list:
How to Get Best Site Performance
Select the China site (in Chinese or English) for best site performance. Other MathWorks country sites are not optimized for visits from your location.
Americas
- América Latina (Español)
- Canada (English)
- United States (English)
Europe
- Belgium (English)
- Denmark (English)
- Deutschland (Deutsch)
- España (Español)
- Finland (English)
- France (Français)
- Ireland (English)
- Italia (Italiano)
- Luxembourg (English)
- Netherlands (English)
- Norway (English)
- Österreich (Deutsch)
- Portugal (English)
- Sweden (English)
- Switzerland
- United Kingdom (English)