Navigation
API > API/Plugins > API/Plugins/LearningAgentsTraining > API/Plugins/LearningAgentsTraining/ULearningAgentsTrainer
References
| Module | LearningAgentsTraining |
| Header | /Engine/Plugins/Experimental/LearningAgents/Source/LearningAgentsTraining/Public/LearningAgentsTrainer.h |
| Include | #include "LearningAgentsTrainer.h" |
| Source | /Engine/Plugins/Experimental/LearningAgents/Source/LearningAgentsTraining/Private/LearningAgentsTrainer.cpp |
UFUNCTION&40;BlueprintCallable, Category&61;"LearningAgents"&41;
void BeginTraining
&40;
const FLearningAgentsTrainerTrainingSettings & TrainerTrainingSettings,
const FLearningAgentsTrainerGameSettings & TrainerGameSettings,
const FLearningAgentsTrainerPathSettings & TrainerPathSettings,
const FLearningAgentsCriticSettings & CriticSettings,
const bool bReinitializePolicyNetwork,
const bool bReinitializeCriticNetwork,
const bool bResetAgentsOnBegin
&41;
Remarks
Begins the training process with the provided settings.
Parameters
| Name | Description |
|---|---|
| TrainerTrainingSettings | The settings for this training run. |
| TrainerGameSettings | The settings that will affect the game's simulation. |
| TrainerPathSettings | The path settings used by the trainer. |
| CriticSettings | The settings for the critic (if we are using one). |
| bReinitializePolicyNetwork | If true, reinitialize the policy. Set this to false if your policy is pre-trained, e.g. with imitation learning. |
| bReinitializeCriticNetwork | If true, reinitialize the critic. Set this to false if your critic is pre-trained. |
| bResetAgentsOnBegin | If true, reset all agents at the beginning of training. |