Data-Driven Control of Unknown Systems: A Linear Programming Approach


Date

2020-11

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

We consider the problem of discounted optimal state-feedback regulation for general unknown deterministic discrete-time systems. It is well known that open-loop instability of systems, non-quadratic cost functions and complex nonlinear dynamics, as well as the on-policy behavior of many reinforcement learning (RL) algorithms, make the design of model-free optimal adaptive controllers a challenging task. We depart from commonly used least-squares and neural network approximation methods in conventional model-free control theory, and propose a novel family of data-driven optimization algorithms based on linear programming, off-policy Q-learning and randomized experience replay. We develop both policy iteration (PI) and value iteration (VI) methods to compute an approximate optimal feedback controller with high precision and without the knowledge of a system model and stage cost function. Simulation studies confirm the effectiveness of the proposed methods.

Publication status

published

Book title

21st IFAC World Congress

Volume

53 (2)

Pages / Article No.

7 - 13

Publisher

Elsevier

Event

1st Virtual IFAC World Congress (IFAC-V 2020)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Linear programming; Q-learning; Approximate dynamic programming; Data-driven control

Organisational unit

03751 - Lygeros, John / Lygeros, John check_circle

Notes

Due to the Coronavirus (COVID-19) the 21st IFAC World Congress 2020 became the 1st Virtual IFAC World Congress (IFAC-V 2020).

Funding

Related publications and datasets