1. Epic GamesDeveloper
  3. PolicyWindowSize

PolicyWindowSize

The number of consecutive steps of observations and actions over which to train the policy.

API > API/Plugins > API/Plugins/LearningAgentsTraining > API/Plugins/LearningAgentsTraining/FLearningAgentsPPOTrainingSettin-

Syntax

UPROPERTY (EditAnywhere, Category="LearningAgents", Meta=(ClampMin="1", UIMin="1", UIMax="128"))  
int32 PolicyWindowSize

Remarks

The number of consecutive steps of observations and actions over which to train the policy. Increasing this value will encourage the policy to use its memory effectively. Too large and training can become slow and unstable.

Ask questions and help your peers Developer Forums

Write your own tutorials or read those from others Learning Library

On this page