Combining Model-Based and Model-Free Methods for Nonlinear Control: A Provably Convergent Policy Gradient Approach
Creators
Abstract
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.
Attached Files
Submitted - 2006.07476.pdf
Files
2006.07476.pdf
Files
(935.3 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:50db38c9018fb542b36cb0e48479b828
|
935.3 kB | Preview Download |
Additional details
Identifiers
- Eprint ID
- 104239
- Resolver ID
- CaltechAUTHORS:20200707-095652399
Related works
- Describes
- http://arxiv.org/abs/2006.07476 (URL)
Dates
- Created
-
2020-07-07Created from EPrint's datestamp field
- Updated
-
2023-06-02Created from EPrint's last_modified field