Open access
Date
2020-11Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
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. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000461397Publication status
publishedExternal links
Book title
21st IFAC World CongressJournal / series
IFAC-PapersOnLineVolume
Pages / Article No.
Publisher
ElsevierEvent
Subject
Linear programming; Q-learning; Approximate dynamic programming; Data-driven controlOrganisational unit
03751 - Lygeros, John / Lygeros, John
Notes
Due to the Coronavirus (COVID-19) the 21st IFAC World Congress 2020 became the 1st Virtual IFAC World Congress (IFAC-V 2020).More
Show all metadata
ETH Bibliography
yes
Altmetrics