Navigation
API > API/Plugins > API/Plugins/Learning
Neural-network based policy object. Stores various settings and intermediate storage required to evaluate the given network for the provided number of instances.
| Name | FNeuralNetworkPolicy |
| Type | struct |
| Header File | /Engine/Plugins/Experimental/LearningAgents/Source/Learning/Public/LearningPolicy.h |
| Include Path | #include "LearningPolicy.h" |
Syntax
struct FNeuralNetworkPolicy
Constructors
| Name | Remarks | Include Path | Unreal Specifiers |
|---|---|---|---|
FNeuralNetworkPolicy
(
const int32 InMaxInstanceNum, |
Create a new Policy Object which takes the encoded observation state, and the memory state, and outputs the encoded action state. | LearningPolicy.h |
Variables
Protected
| Name | Type | Remarks | Include Path | Unreal Specifiers |
|---|---|---|---|---|
| ActionEncodedNum | int32 | LearningPolicy.h | ||
| Input | TLearningArray< 2, float > | LearningPolicy.h | ||
| MemoryStateNum | int32 | LearningPolicy.h | ||
| NeuralNetworkFunction | TSharedPtr< FNeuralNetworkFunction > | LearningPolicy.h | ||
| ObservationEncodedNum | int32 | LearningPolicy.h | ||
| Output | TLearningArray< 2, float > | LearningPolicy.h |
Functions
Public
| Name | Remarks | Include Path | Unreal Specifiers |
|---|---|---|---|
void Evaluate
(
TLearningArrayView< 2, float > OutputActionVectorsEncoded, |
Evaluate the Policy | LearningPolicy.h | |
const TSharedPtr< FNeuralNetwork > & GetNeuralNetwork() |
Gets the NeuralNetwork associated with this Policy | LearningPolicy.h | |
void UpdateNeuralNetwork
(
const TSharedPtr< FNeuralNetwork >& NewNeuralNetwork |
Sets the NeuralNetwork and re-creates the NeuralNetworkInference object | LearningPolicy.h |