1. Add some extra comments (Better reading with Extention: Beteer Comments)
2. Modified the "main" part in environment.py, changed env "Load3RL" into "EnvPMSM"
3. Created "rl_state_space_control_testRL.py" to implement simple RL algorithm-DDPG to check whether environment can run correctly or not. Also tried to use WandB to keep the data and visualize the training progress. But missed something, just to test.

Question: Didnt set case which would terminate the action.