Decode and Sample Actions

Decode and Sample Actions

BlueprintAPI > BlueprintAPI/LearningAgents

Decodes and samples action vectors using the Decoder network. This should be called after both MakeActionModifiers and EvaluatePolicy, but before PerformActions.

Target is Learning Agents Policy

Inputs

Type Name Description
exec In  
object Target  
real Action Noise Scale Scale of the action noise to use during sampling. Set this to zero to always sample the mean (expected) action.

Outputs

Type Name Description
exec Out  

Ask questions and help your peers Developer Forums

Write your own tutorials or read those from others Learning Library

On this page