i am trying tune PID using reinforcement learning for 2 inputs and 2 output system.. but my code throws error. i used the code from mathworks for SISO-PID using reinforcement

i am not sure in how to define the num of observations and actions for multi agent system

Error using rlSimulinkEnv>localValidateIOSpecs

Invalid size or type for observation specification.

Error in rlSimulinkEnv (line 90)

localValidateIOSpecs(numAgents,observationInfo,actionInfo);

Error in rlcodemimo2222>localCreatePIDEnv (line 148)

env = rlSimulinkEnv(mdl,blks,obsInfo,actInfo);

Error in rlcodemimo2222 (line 10)

[env,obsInfo,actInfo] = localCreatePIDEnv(mdl);

[Sanju]

can you please share the code for better understanding and reproduction of the issue.