CrackRobotics

Learning Algorithms, step 4

Policy gradient (REINFORCE)

Learn to throw a ball into the cup by trial and error: sample throws around your best guess and move towards the ones that land closer.

Likelihood-ratio gradientBaselineLearning-rate decay

This step is part of CrackRobotics Pro

Pick & Place and the first step of every other lesson are free. Pro unlocks every other step for $39 a month, and you can cancel anytime.