Combining Model-Based and Model-Free Methods for Nonlinear Control: A Provably Convergent Policy Gradient Approach
This addresses a key bottleneck in nonlinear control for robotics and autonomous systems, offering a practical solution with theoretical guarantees, though it is incremental in integrating existing paradigms.
The paper tackles the problem of poor sample complexity and limited convergence guarantees in model-free control by combining model-based and model-free methods, showing that this hybrid approach outperforms model-based controllers and achieves provable convergence to near-global optimality.
Model-free learning-based control methods have seen great success recently. However, such methods typically suffer from poor sample complexity and limited convergence guarantees. This is in sharp contrast to classical model-based control, which has a rich theory but typically requires strong modeling assumptions. In this paper, we combine the two approaches to achieve the best of both worlds. We consider a dynamical system with both linear and non-linear components and develop a novel approach to use the linear model to define a warm start for a model-free, policy gradient method. We show this hybrid approach outperforms the model-based controller while avoiding the convergence issues associated with model-free approaches via both numerical experiments and theoretical analyses, in which we derive sufficient conditions on the non-linear component such that our approach is guaranteed to converge to the (nearly) global optimal controller.