Reinforcement Learning offers a very general framework for learning controllers, but its effectiveness is closely tied to the controller parameterization used. Especially when learning feedback ...

REINFORCE algorithm requires a differentiable policy parameterization. In theory, any function approxiamtion algorithm would work. For this implementation, I choose tile coding with linear ...

Reinforcement Learning offers a very general framework for learning controllers, but its effectiveness is closely tied to the controller parameterization used. Especially when learning feedback ...