Configuration Path Control

The fundamental ingredient of our approach is a control policy stabilization around desired configuration paths (time-reparameterized trajectories) that can be rigorously The past decade has seen successful applications of justified in the high gain limit (HGL). We call deep neural networks (NN) to various machine learning this approach Configuration Path Control (CPC). It has tasks, such as image classification [18, 20], speech some overlap with the zero dynamics (ZD) concept [3], recognition [12] and language translation [32, 37]. In the which is central to the Hybrid Zero Dynamics (HZD) field of reinforcement learning (RL), the employment of framework in the context of bipedal walkers [9, 36]. We deep NNs as expressive function approximators has been reinterpret the derived CPC control law in the language crucial in tackling many difficult problems involving an of the HZD literature, by re-stating it in terms of the agent interacting with its environment with the goal of reparameterization invariant virtual constraints.