Navigation
API > API/Plugins > API/Plugins/Learning > API/Plugins/Learning/FNeuralNetworkPolicy
References
| Module | Learning |
| Header | /Engine/Plugins/Experimental/LearningAgents/Source/Learning/Public/LearningPolicy.h |
| Include | #include "LearningPolicy.h" |
| Source | /Engine/Plugins/Experimental/LearningAgents/Source/Learning/Private/LearningPolicy.cpp |
FNeuralNetworkPolicy
(
const int32 InMaxInstanceNum,
const int32 InObservationEncodedNum,
const int32 InActionEncodedNum,
const int32 InMemoryStateNum,
const TSharedPtr < FNeuralNetwork > & InNeuralNetwork,
const FNeuralNetworkInferenceSettings & InInferenceSettings
)
Remarks
Create a new Policy Object which takes the encoded observation state, and the memory state, and outputs the encoded action state.
Parameters
| Name | Description |
|---|---|
| InMaxInstanceNum | Maximum number of instances |
| InObservationEncodedNum | Size of the encoded observation vector |
| InActionEncodedNum | Size of the encoded action vector |
| InMemoryStateNum | Size of the memory state |
| InNeuralNetwork | Neural network object |
| InInferenceSettings | Inference settings |