rlPGAgentOptions

Create options for PG agent

Syntax

opt = rlPGAgentOptions
opt = rlPGAgentOptions(Name,Value)

Description

example

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

opt = rlPGAgentOptions(Name,Value) creates a PG options object using the specified name-value pairs to override default property values.

Examples

collapse all

Create a PG agent options object, specifying the discount factor.

opt = rlPGAgentOptions('DiscountFactor',0.9)
opt = 

  rlPGAgentOptions with properties:

          UseBaseline: 1
    EntropyLossWeight: 0
           SampleTime: 1
       DiscountFactor: 0.9000

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

opt.SampleTime = 0.5;

Input Arguments

collapse all

Name-Value Pair Arguments

Specify optional comma-separated pairs of Name,Value arguments. Name is the argument name and Value is the corresponding value. Name must appear inside quotes. You can specify several name and value pair arguments in any order as Name1,Value1,...,NameN,ValueN.

Example: "DiscountFactor",0.95

Instruction to use baseline for learning, specified as the comma-separated pair consisting of 'UseBaseline' and logical true or false. WhenUseBaseline is true, you must specify a critic network as the baseline function approximator.

In general, for simpler problems with smaller actor networks, PG agents work better without a baseline.

Sample time of agent, specified as the comma-separated pair consisting of 'SampleTime' and a numeric value.

Discount factor applied to future rewards during training, specified as the comma-separated pair consisting of 'DiscountFactor' and a positive numeric value less than or equal to 1.

Entropy loss weight, specified as the comma-separated pair consisting of 'EntropyLossWeight' and a scalar value between 0 and 1. A higher 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.

The entropy loss function for episode step t is:

Ht=Ek=1Mμk(St|θμ)lnμk(St|θμ)

Here:

  • E is the entropy loss weight.

  • M is the number of possible actions.

  • μk(St) is the probability of taking action Ak following the current policy.

When gradients are computed during training, an additional gradient component is computed for minimizing this loss function.

Output Arguments

collapse all

PG agent options, returned as an rlPGAgentOptions object. The object properties are described in Name-Value Pair Arguments.

See Also

Functions

Introduced in R2019a