DeepAI AI Chat
Log In Sign Up

A stabilizing reinforcement learning approach for sampled systems with partially unknown models

by   Lukas Beckenbach, et al.
TU Chemnitz

Reinforcement learning is commonly associated with training of reward-maximizing (or cost-minimizing) agents, in other words, controllers. It can be applied in model-free or model-based fashion, using a priori or online collected system data to train involved parametric architectures. In general, online reinforcement learning does not guarantee closed loop stability unless special measures are taken, for instance, through learning constraints or tailored training rules. Particularly promising are hybrids of reinforcement learning with "classical" control approaches. In this work, we suggest a method to guarantee practical stability of the system-controller closed loop in a purely online learning setting, i.e., without offline training. Moreover, we assume only partial knowledge of the system model. To achieve the claimed results, we employ techniques of classical adaptive control. The implementation of the overall control scheme is provided explicitly in a digital, sampled setting. That is, the controller receives the state of the system and computes the control action at discrete, specifically, equidistant moments in time. The method is tested in adaptive traction control and cruise control where it proved to significantly reduce the cost.


page 1

page 7


Self-optimizing adaptive optics control with Reinforcement Learning for high-contrast imaging

Current and future high-contrast imaging instruments require extreme ada...

On stabilizing reinforcement learning without Lyapunov functions

Reinforcement learning remains one of the major directions of the contem...

Safe Control and Learning Using Generalized Action Governor

This paper introduces the Generalized Action Governor, which is a superv...

Online Selection of Diverse Committees

Citizens' assemblies need to represent subpopulations according to their...

A Reinforcement Learning Approach for Transient Control of Liquid Rocket Engines

Nowadays, liquid rocket engines use closed-loop control at most near ste...

Closed-Loop Control of Direct Ink Writing via Reinforcement Learning

Enabling additive manufacturing to employ a wide range of novel, functio...