Solving the swing-up and balance task for the Acrobot and Pendubot with SAC
This work addresses a specific control problem in robotics for the AI Olympics competition, representing an incremental improvement by applying existing methods to known tasks.
The authors tackled the swing-up and balance task for the Acrobot and Pendubot using a hybrid approach combining SAC reinforcement learning with an LQR controller, achieving competitive scores in performance and robustness for both scenarios.
We present a solution of the swing-up and balance task for the pendubot and acrobot for the participation in the AI Olympics competition at IJCAI 2023. Our solution is based on the Soft Actor Crtic (SAC) reinforcement learning (RL) algorithm for training a policy for the swing-up and entering the region of attraction of a linear quadratic regulator(LQR) controller for stabilizing the double pendulum at the top position. Our controller achieves competitive scores in performance and robustness for both, pendubot and acrobot, problem scenarios.