How can i set variable learning rate of actors and critics in Reinforcement Learning Toolbox?

In the rlOptimizerOptions of Reinforcement Learning Toolbox,learning rate used in training the actor or critic function approximator, specified as a positive scalar,how can i set variable learning rate of actors and critics in Reinforcement Learning Toolbox?

[Matteo D'Ambrosio]

Hello,

The variable learning rate options seem to only be implemented for training of deep neural networks. Even looking through the documentation, I've never been able to find variable learning rate options in Matlab's RL toolbox.