Reinforcement Learning in machine learning

Thread Starter

goutham1995

Joined Feb 18, 2018
104
Hello,

I was watching some videos on inverted pendulum ( cart-pole balancing system) and wanted to know what exactly does it try to learn. Does it only try to tune PID values after learning or does it have another algorithm working behind it? The reason I ask is to compare the performance of PID with that of machine learning. If machine learning for inverted pendulum is only tuning PID , then the performance will be the same and I don't have to do the procedure.
 
Top