Energy harvesting Sensor nodes -- 2

Hello, I need to use MATLAB to modify the code for my project (Using Markov Decision Process) . In this system, 2 nodes (N1,N2) are communicated , where both will be able to send data to each other. For this, i consider a set of action ( a=0,1,2,3,4,5,6,7,8) ,when a=0 ,there will be no transmission, when a=1,2,3,4, N1 will forward data to N2 and when a =5,6,7,8 there wilI have backward data to N2. I use MDP ( Markov Decision Process ) to formulate this problem. Thanks! Best Regards!