EpsilonClip

Navigation

API > API/Plugins > API/Plugins/LearningAgentsTraining > API/Plugins/LearningAgentsTraining/FLearningAgentsTrainerTrainingSe-

Syntax

UPROPERTY&40;EditAnywhere, Category&61;"LearningAgents",  
          Meta&61;&40;ClampMin&61;"0.0", ClampMax&61;"1.0", UIMin&61;"0.0", UIMax&61;"1.0"&41;&41;  
float EpsilonClip  
Copy full snippet

Remarks

Clipping ratio to apply to policy updates. Keeps the training "on-policy". Larger values may speed up training at the cost of stability. Conversely, too small values will keep the policy from being able to learn an optimal policy.