Global parameters / data store memory with RL agent block Simulink

Question

0 个投票

I am using a Simulink model for reinforcement learning (RL). I have created the environmnet using createdIntegratedEnv. I would like to calculate the change in error at each sample time step and feed this as an observation to the RL agent. I have tried using a data store memory block in the model environmnet (i.e. the environment which models the plant considered) to keep track of the previous error value, however I receive an error stating that I cannot use this block with a RL environment.

Any insight on how to update a global parameter in the model within the RL environment would be greatly appreciated.