Navigation
API > API/Plugins > API/Plugins/Learning
Inheritance Hierarchy
- FRewardObject
- FConditionalConstantReward
- FConstantPenalty
- FConstantReward
- FFacingDirectionAngularDifferencePenalty
- FFacingTowardsTargetAngularDifferencePenalty
- FFloatReward
- FLocalDirectionalVelocityReward
- FPlanarPositionDifferencePenalty
- FPositionArraySimilarityReward
- FPositionDifferencePenalty
- FScalarAngularVelocitySimilarityReward
- FScalarPositionSimilarityReward
- FScalarRotationSimilarityReward
- FScalarVelocityReward
- FSpringInertializationPenalty
- FSumReward
- FVectorAverageMagnitudePenalty
- FVelocityDifferencePenalty
References
| Module | Learning |
| Header | /Engine/Plugins/Experimental/LearningAgents/Source/Learning/Public/LearningRewardObject.h |
| Include | #include "LearningRewardObject.h" |
Syntax
struct FRewardObject
Remarks
Base class for an object which computes a reward or penalty value from a set of other arrays. Here, all data is assumed to be stored in a `FArrayMap_ object to make the processing of multiple instances efficient.
Variables
| Type | Name | Description | |
|---|---|---|---|
 |
TSharedRef< FArrayMap > | InstanceData | |
 |
TArrayMapHandle< 1, float > | RewardHandle |
Constructors
| Type | Name | Description | |
|---|---|---|---|
 |
FRewardObject
(
const FName& InIdentifier, |
Destructors
| Type | Name | Description | |
|---|---|---|---|
  |
Functions
| Type | Name | Description | |
|---|---|---|---|
 |
void | ||
 |
TLearningArrayView< 1, float > | RewardBuffer () |