rlACAgentOptions

Options for AC agent

Description

Use an rlACAgentOptions object to specify options for creating actor-critic (AC) agents. To create an actor-critic agent, use rlACAgent

For more information see Actor-Critic Agents.

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

Creation

Syntax

opt = rlACAgentOptions

opt = rlACAgentOptions(Name,Value)

Description

opt = rlACAgentOptions creates a default option set for an AC agent. You can modify the object properties using dot notation.

opt = rlACAgentOptions(Name,Value) sets option properties using name-value pairs. For example, rlDQNAgentOptions('DiscountFactor',0.95) creates an option set with a discount factor of 0.95. You can specify multiple name-value pairs. Enclose each property name in quotes.

Properties

NumStepsToLookAhead — Number of steps ahead

32 (default) | positive integer

Number of steps the agent interacts with the environment before learning from its experience, specified as a positive integer. When the agent uses a recurrent neural network, NumStepsToLookAhead is treated as the training trajectory length.

EntropyLossWeight — Entropy loss weight

0 (default) | scalar value between 0 and 1

Entropy loss weight, specified as 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.

For episode step t, the entropy loss function, which is added to the loss function for actor updates, is:

$$H_t=E{\displaystyle \sum _{k=1}^M{\mu }_k\left(S_t|{\theta }_{\mu }\right)}\ln {\mu }_k\left(S_t|{\theta }_{\mu }\right)$$

Here:

• E is the entropy loss weight.

• M is the number of possible actions.

• μ_k(S_t|θ_μ) is the probability of taking action A_k when in state S_t following the current policy.

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

UseDeterministicExploitation — Use action with maximum likelihood

false (default) | true

Option to return the action with maximum likelihood for simulation and policy generation, specified as a logical value. When UseDeterministicExploitation is set to true, the action with maximum likelihood is always used in sim and generatePolicyFunction, which casues the agent to behave deterministically.

When UseDeterministicExploitation is set to false, the agent samples actions from probability distributions, which causes the agent to behave stochastically.

SampleTime — Sample time of agent

1 (default) | positive scalar

Sample time of agent, specified as a positive scalar.

Within a Simulink^® environment, the agent gets executed every SampleTime seconds of simulation time.

Within a MATLAB^® environment, the agent gets executed every time the environment advances. However, SampleTime is the time interval between consecutive elements in the output experience returned by sim or train.

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.

Object Functions

rlACAgent

Actor-critic reinforcement learning agent

Examples

Create AC Agent Options Object

Create an AC agent options object, specifying the discount factor.

opt = rlACAgentOptions('DiscountFactor',0.95)

opt = 
  rlACAgentOptions with properties:

             NumStepsToLookAhead: 32
               EntropyLossWeight: 0
    UseDeterministicExploitation: 0
                      SampleTime: 1
                  DiscountFactor: 0.9500

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

opt.SampleTime = 0.5;

Compatibility Considerations

Default value for NumStepsToLookAhead changed to 32

Behavior change in future release

A value of 32 for this property should work better than 1 for most environments. If you nave MATLAB R2020b or a later version and you want to reproduce how rlACAgent behaved on versions prior to R2020b, set this value to 1.