Fix code for Reinforcement learning project

I have developed a code for reinforment learning for power system. However the code is facing some issues. 1. The diagrams plotted are not making sense, especially for the cost are all the same for all scenarios. 2. I am also suspect the stability is not correct. 3. There is one diagrams at the end that is not capturing the result. Basically, I want you to check the code and correct it for me. As simple as that. I am using Kaggle for the code.