Overview / Usage

Cart Pole Balancing Problem is one of the standard classical control problem. Building an AI Reinforcement learning agent to balance the pole connected with one joint on top of the moving cart is a challenging problem. This live demo showcases the working of the state of the art adaptive actor critic game controller. It has applications in designing future feedback controllers.

The AI Reinforcement agent is able to balance the pole successfully for infinite time steps with the designed algorithm for 100 test runs. The projects runs 100 times faster in few minutes in intelpython. However, it takes a day to run in MATLAB.

The algorithm is the modified version from the paper "Online learning control by association and reinforcement" with performance optimization to balance the pole in the first trial for all the constraints.