Navigation
API > API/Plugins > API/Plugins/LearningAgents
The configurable settings for a ULearningAgentsPolicy.
| Name | FLearningAgentsPolicySettings |
| Type | struct |
| Header File | /Engine/Plugins/Experimental/LearningAgents/Source/LearningAgents/Public/LearningAgentsPolicy.h |
| Include Path | #include "LearningAgentsPolicy.h" |
Syntax
USTRUCT (BlueprintType , Category="LearningAgents")
struct FLearningAgentsPolicySettings
Variables
Public
| Name | Type | Remarks | Include Path | Unreal Specifiers |
|---|---|---|---|---|
| ActivationFunction | ELearningAgentsActivationFunction | Activation function to use on hidden layers of the policy network | LearningAgentsPolicy.h |
|
| bUseParallelEvaluation | bool | If true, policy can be evaluated on multiple threads to speed up large agent counts. | LearningAgentsPolicy.h |
|
| HiddenLayerNum | int32 | Number of hidden layers for policy network. | LearningAgentsPolicy.h |
|
| HiddenLayerSize | int32 | Number of neurons in each hidden layer of the policy network | LearningAgentsPolicy.h |
|
| InitialEncodedActionScale | float | Initial scale for encoded actions. | LearningAgentsPolicy.h |
|
| MemoryCell | ELearningAgentsMemoryCell | The type of memory cell to use. | LearningAgentsPolicy.h |
|
| MemoryStateSize | int32 | Number of neurons in the memory state of the policy network | LearningAgentsPolicy.h |
|