Navigation
API > API/Plugins > API/Plugins/LearningAgentsTraining
References
| Module | LearningAgentsTraining |
| Header | /Engine/Plugins/Experimental/LearningAgents/Source/LearningAgentsTraining/Public/LearningAgentsImitationTrainer.h |
| Include | #include "LearningAgentsImitationTrainer.h" |
Syntax
USTRUCT&40;BlueprintType, Category&61;"LearningAgents"&41;
struct FLearningAgentsImitationTrainerTrainingSettings
Remarks
The configurable settings for the training process.
Variables
| Type | Name | Description | |
|---|---|---|---|
   |
uint32 | BatchSize | Batch size to use for training. |
   |
bool | bUseTensorboard | If true, TensorBoard logs will be emitted to the intermediate directory. |
   |
ELearningAgentsTrainerDevice | Device | The device to train on. |
   |
float | LearningRate | Learning rate of the policy network. Typical values are between 0.001 and 0.0001. |
   |
float | LearningRateDecay | Ratio by which to decay the learning rate every 1000 iterations. |
   |
int32 | NumberOfIterations | The number of iterations to run before ending training. |
   |
int32 | RandomSeed | The seed used for any random sampling the trainer will perform, e.g. for weight initialization. |
   |
float | WeightDecay | Amount of weight decay to apply to the network. |