Tracking Control for a Spherical Pendulum via Curriculum Reinforcement Learning
This work addresses the challenge of automating curriculum generation for reinforcement learning in non-linear robot control tasks, which is incremental as it builds on existing curriculum RL methods with an improved optimization scheme.
The paper tackled the problem of learning a tracking controller for a spherical pendulum on a robotic arm using reinforcement learning, and the result was that the learned policy matched the performance of an optimal control baseline on the real system, with faster and more robust learning compared to a baseline without structured curricula.
Reinforcement Learning (RL) allows learning non-trivial robot control laws purely from data. However, many successful applications of RL have relied on ad-hoc regularizations, such as hand-crafted curricula, to regularize the learning performance. In this paper, we pair a recent algorithm for automatically building curricula with RL on massively parallelized simulations to learn a tracking controller for a spherical pendulum on a robotic arm via RL. Through an improved optimization scheme that better respects the non-Euclidean task structure, we allow the method to reliably generate curricula of trajectories to be tracked, resulting in faster and more robust learning compared to an RL baseline that does not exploit this form of structured learning. The learned policy matches the performance of an optimal control baseline on the real system, demonstrating the potential of curriculum RL to jointly learn state estimation and control for non-linear tracking tasks.